DeepGazeIIE(
  (models): ModuleList(
    (0): DeepGazeIIIMixture(
      (features): FeatureExtractor(
        (features): RGBShapeNetC(
          (0): Normalizer()
          (1): Sequential(
            (module): ResNet(
              (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
              (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              (relu): ReLU(inplace=True)
              (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
              (layer1): Sequential(
                (0): Bottleneck(
                  (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                  (downsample): Sequential(
                    (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                    (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  )
                )
                (1): Bottleneck(
                  (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
                (2): Bottleneck(
                  (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
              )
              (layer2): Sequential(
                (0): Bottleneck(
                  (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                  (downsample): Sequential(
                    (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
                    (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  )
                )
                (1): Bottleneck(
                  (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
                (2): Bottleneck(
                  (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
                (3): Bottleneck(
                  (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
              )
              (layer3): Sequential(
                (0): Bottleneck(
                  (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                  (downsample): Sequential(
                    (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
                    (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  )
                )
                (1): Bottleneck(
                  (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
                (2): Bottleneck(
                  (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
                (3): Bottleneck(
                  (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
                (4): Bottleneck(
                  (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
                (5): Bottleneck(
                  (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
              )
              (layer4): Sequential(
                (0): Bottleneck(
                  (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                  (downsample): Sequential(
                    (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
                    (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  )
                )
                (1): Bottleneck(
                  (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
                (2): Bottleneck(
                  (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                  (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu): ReLU(inplace=True)
                )
              )
              (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
              (fc): Linear(in_features=2048, out_features=1000, bias=True)
            )
          )
        )
      )
      (saliency_networks): ModuleList(
        (0): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (1): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (2): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (3): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (4): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (5): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (6): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (7): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (8): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (9): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (10): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (11): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (12): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (13): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (14): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (15): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (16): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (17): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (18): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (19): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (20): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (21): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (22): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (23): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (24): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (25): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (26): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (27): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (28): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (29): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
      )
      (scanpath_networks): ModuleList(
        (0): None
        (1): None
        (2): None
        (3): None
        (4): None
        (5): None
        (6): None
        (7): None
        (8): None
        (9): None
        (10): None
        (11): None
        (12): None
        (13): None
        (14): None
        (15): None
        (16): None
        (17): None
        (18): None
        (19): None
        (20): None
        (21): None
        (22): None
        (23): None
        (24): None
        (25): None
        (26): None
        (27): None
        (28): None
        (29): None
      )
      (fixation_selection_networks): ModuleList(
        (0): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (1): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (2): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (3): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (4): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (5): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (6): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (7): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (8): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (9): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (10): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (11): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (12): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (13): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (14): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (15): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (16): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (17): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (18): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (19): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (20): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (21): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (22): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (23): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (24): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (25): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (26): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (27): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (28): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (29): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
      )
      (finalizers): ModuleList(
        (0): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (1): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (2): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (3): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (4): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (5): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (6): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (7): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (8): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (9): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (10): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (11): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (12): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (13): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (14): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (15): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (16): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (17): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (18): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (19): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (20): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (21): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (22): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (23): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (24): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (25): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (26): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (27): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (28): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (29): Finalizer(
          (gauss): GaussianFilterNd()
        )
      )
    )
    (1): DeepGazeIIIMixture(
      (features): FeatureExtractor(
        (features): RGBEfficientNetB5(
          (0): Normalizer()
          (1): EfficientNet(
            (_conv_stem): Conv2dStaticSamePadding(
              3, 48, kernel_size=(3, 3), stride=(2, 2), bias=False
              (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)
            )
            (_bn0): BatchNorm2d(48, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
            (_blocks): ModuleList(
              (0): MBConvBlock(
                (_depthwise_conv): Conv2dStaticSamePadding(
                  48, 48, kernel_size=(3, 3), stride=[1, 1], groups=48, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(48, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  48, 12, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  12, 48, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  48, 24, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (1): MBConvBlock(
                (_depthwise_conv): Conv2dStaticSamePadding(
                  24, 24, kernel_size=(3, 3), stride=(1, 1), groups=24, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  24, 6, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  6, 24, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (2): MBConvBlock(
                (_depthwise_conv): Conv2dStaticSamePadding(
                  24, 24, kernel_size=(3, 3), stride=(1, 1), groups=24, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  24, 6, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  6, 24, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (3): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  144, 144, kernel_size=(3, 3), stride=[2, 2], groups=144, bias=False
                  (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  144, 6, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  6, 144, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  144, 40, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (4): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  240, 240, kernel_size=(3, 3), stride=(1, 1), groups=240, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  240, 10, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  10, 240, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (5): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  240, 240, kernel_size=(3, 3), stride=(1, 1), groups=240, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  240, 10, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  10, 240, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (6): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  240, 240, kernel_size=(3, 3), stride=(1, 1), groups=240, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  240, 10, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  10, 240, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (7): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  240, 240, kernel_size=(3, 3), stride=(1, 1), groups=240, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  240, 10, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  10, 240, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(40, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (8): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  240, 240, kernel_size=(5, 5), stride=[2, 2], groups=240, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 2, 1, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(240, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  240, 10, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  10, 240, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  240, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(64, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (9): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(384, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  384, 384, kernel_size=(5, 5), stride=(1, 1), groups=384, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(384, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  384, 16, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  16, 384, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(64, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (10): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(384, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  384, 384, kernel_size=(5, 5), stride=(1, 1), groups=384, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(384, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  384, 16, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  16, 384, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(64, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (11): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(384, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  384, 384, kernel_size=(5, 5), stride=(1, 1), groups=384, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(384, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  384, 16, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  16, 384, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(64, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (12): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(384, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  384, 384, kernel_size=(5, 5), stride=(1, 1), groups=384, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(384, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  384, 16, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  16, 384, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(64, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (13): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(384, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  384, 384, kernel_size=(3, 3), stride=[2, 2], groups=384, bias=False
                  (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(384, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  384, 16, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  16, 384, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(128, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (14): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  128, 768, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  768, 768, kernel_size=(3, 3), stride=(1, 1), groups=768, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  768, 32, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  32, 768, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(128, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (15): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  128, 768, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  768, 768, kernel_size=(3, 3), stride=(1, 1), groups=768, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  768, 32, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  32, 768, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(128, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (16): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  128, 768, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  768, 768, kernel_size=(3, 3), stride=(1, 1), groups=768, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  768, 32, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  32, 768, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(128, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (17): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  128, 768, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  768, 768, kernel_size=(3, 3), stride=(1, 1), groups=768, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  768, 32, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  32, 768, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(128, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (18): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  128, 768, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  768, 768, kernel_size=(3, 3), stride=(1, 1), groups=768, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  768, 32, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  32, 768, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(128, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (19): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  128, 768, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  768, 768, kernel_size=(3, 3), stride=(1, 1), groups=768, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  768, 32, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  32, 768, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(128, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (20): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  128, 768, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  768, 768, kernel_size=(5, 5), stride=[1, 1], groups=768, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(768, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  768, 32, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  32, 768, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  768, 176, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(176, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (21): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  176, 1056, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1056, 1056, kernel_size=(5, 5), stride=(1, 1), groups=1056, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1056, 44, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  44, 1056, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1056, 176, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(176, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (22): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  176, 1056, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1056, 1056, kernel_size=(5, 5), stride=(1, 1), groups=1056, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1056, 44, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  44, 1056, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1056, 176, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(176, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (23): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  176, 1056, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1056, 1056, kernel_size=(5, 5), stride=(1, 1), groups=1056, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1056, 44, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  44, 1056, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1056, 176, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(176, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (24): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  176, 1056, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1056, 1056, kernel_size=(5, 5), stride=(1, 1), groups=1056, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1056, 44, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  44, 1056, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1056, 176, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(176, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (25): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  176, 1056, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1056, 1056, kernel_size=(5, 5), stride=(1, 1), groups=1056, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1056, 44, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  44, 1056, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1056, 176, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(176, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (26): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  176, 1056, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1056, 1056, kernel_size=(5, 5), stride=(1, 1), groups=1056, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1056, 44, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  44, 1056, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1056, 176, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(176, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (27): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  176, 1056, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1056, 1056, kernel_size=(5, 5), stride=[2, 2], groups=1056, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 2, 1, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1056, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1056, 44, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  44, 1056, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1056, 304, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(304, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (28): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  304, 1824, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1824, 1824, kernel_size=(5, 5), stride=(1, 1), groups=1824, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1824, 76, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  76, 1824, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1824, 304, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(304, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (29): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  304, 1824, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1824, 1824, kernel_size=(5, 5), stride=(1, 1), groups=1824, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1824, 76, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  76, 1824, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1824, 304, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(304, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (30): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  304, 1824, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1824, 1824, kernel_size=(5, 5), stride=(1, 1), groups=1824, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1824, 76, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  76, 1824, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1824, 304, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(304, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (31): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  304, 1824, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1824, 1824, kernel_size=(5, 5), stride=(1, 1), groups=1824, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1824, 76, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  76, 1824, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1824, 304, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(304, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (32): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  304, 1824, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1824, 1824, kernel_size=(5, 5), stride=(1, 1), groups=1824, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1824, 76, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  76, 1824, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1824, 304, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(304, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (33): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  304, 1824, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1824, 1824, kernel_size=(5, 5), stride=(1, 1), groups=1824, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1824, 76, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  76, 1824, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1824, 304, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(304, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (34): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  304, 1824, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1824, 1824, kernel_size=(5, 5), stride=(1, 1), groups=1824, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1824, 76, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  76, 1824, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1824, 304, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(304, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (35): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  304, 1824, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1824, 1824, kernel_size=(5, 5), stride=(1, 1), groups=1824, bias=False
                  (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)
                )
                (_bn1): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1824, 76, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  76, 1824, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1824, 304, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(304, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (36): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  304, 1824, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  1824, 1824, kernel_size=(3, 3), stride=[1, 1], groups=1824, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(1824, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  1824, 76, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  76, 1824, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  1824, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(512, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (37): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  512, 3072, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(3072, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  3072, 3072, kernel_size=(3, 3), stride=(1, 1), groups=3072, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(3072, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  3072, 128, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  128, 3072, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  3072, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(512, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
              (38): MBConvBlock(
                (_expand_conv): Conv2dStaticSamePadding(
                  512, 3072, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn0): BatchNorm2d(3072, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_depthwise_conv): Conv2dStaticSamePadding(
                  3072, 3072, kernel_size=(3, 3), stride=(1, 1), groups=3072, bias=False
                  (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)
                )
                (_bn1): BatchNorm2d(3072, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_se_reduce): Conv2dStaticSamePadding(
                  3072, 128, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_se_expand): Conv2dStaticSamePadding(
                  128, 3072, kernel_size=(1, 1), stride=(1, 1)
                  (static_padding): Identity()
                )
                (_project_conv): Conv2dStaticSamePadding(
                  3072, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
                  (static_padding): Identity()
                )
                (_bn2): BatchNorm2d(512, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
                (_swish): MemoryEfficientSwish()
              )
            )
            (_conv_head): Conv2dStaticSamePadding(
              512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
              (static_padding): Identity()
            )
            (_bn1): BatchNorm2d(2048, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)
            (_avg_pooling): AdaptiveAvgPool2d(output_size=1)
            (_dropout): Dropout(p=0.4, inplace=False)
            (_fc): Linear(in_features=2048, out_features=1000, bias=True)
            (_swish): MemoryEfficientSwish()
          )
        )
      )
      (saliency_networks): ModuleList(
        (0): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (1): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (2): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (3): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (4): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (5): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (6): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (7): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (8): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (9): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (10): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (11): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (12): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (13): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (14): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (15): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (16): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (17): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (18): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (19): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (20): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (21): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (22): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (23): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (24): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (25): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (26): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (27): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (28): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (29): Sequential(
          (layernorm0): LayerNorm(2416, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2416, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
      )
      (scanpath_networks): ModuleList(
        (0): None
        (1): None
        (2): None
        (3): None
        (4): None
        (5): None
        (6): None
        (7): None
        (8): None
        (9): None
        (10): None
        (11): None
        (12): None
        (13): None
        (14): None
        (15): None
        (16): None
        (17): None
        (18): None
        (19): None
        (20): None
        (21): None
        (22): None
        (23): None
        (24): None
        (25): None
        (26): None
        (27): None
        (28): None
        (29): None
      )
      (fixation_selection_networks): ModuleList(
        (0): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (1): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (2): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (3): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (4): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (5): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (6): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (7): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (8): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (9): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (10): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (11): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (12): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (13): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (14): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (15): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (16): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (17): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (18): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (19): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (20): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (21): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (22): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (23): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (24): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (25): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (26): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (27): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (28): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (29): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
      )
      (finalizers): ModuleList(
        (0): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (1): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (2): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (3): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (4): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (5): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (6): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (7): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (8): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (9): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (10): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (11): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (12): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (13): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (14): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (15): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (16): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (17): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (18): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (19): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (20): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (21): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (22): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (23): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (24): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (25): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (26): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (27): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (28): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (29): Finalizer(
          (gauss): GaussianFilterNd()
        )
      )
    )
    (2): DeepGazeIIIMixture(
      (features): FeatureExtractor(
        (features): RGBDenseNet201(
          (0): Normalizer()
          (1): DenseNet(
            (features): Sequential(
              (conv0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
              (norm0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              (relu0): ReLU(inplace=True)
              (pool0): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
              (denseblock1): _DenseBlock(
                (denselayer1): _DenseLayer(
                  (norm1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer2): _DenseLayer(
                  (norm1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(96, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer3): _DenseLayer(
                  (norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer4): _DenseLayer(
                  (norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer5): _DenseLayer(
                  (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer6): _DenseLayer(
                  (norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
              )
              (transition1): _Transition(
                (norm): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
                (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
              )
              (denseblock2): _DenseBlock(
                (denselayer1): _DenseLayer(
                  (norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer2): _DenseLayer(
                  (norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer3): _DenseLayer(
                  (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer4): _DenseLayer(
                  (norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer5): _DenseLayer(
                  (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer6): _DenseLayer(
                  (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer7): _DenseLayer(
                  (norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer8): _DenseLayer(
                  (norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer9): _DenseLayer(
                  (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer10): _DenseLayer(
                  (norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer11): _DenseLayer(
                  (norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer12): _DenseLayer(
                  (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
              )
              (transition2): _Transition(
                (norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
                (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
              )
              (denseblock3): _DenseBlock(
                (denselayer1): _DenseLayer(
                  (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer2): _DenseLayer(
                  (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer3): _DenseLayer(
                  (norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer4): _DenseLayer(
                  (norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer5): _DenseLayer(
                  (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer6): _DenseLayer(
                  (norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer7): _DenseLayer(
                  (norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer8): _DenseLayer(
                  (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer9): _DenseLayer(
                  (norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer10): _DenseLayer(
                  (norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer11): _DenseLayer(
                  (norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer12): _DenseLayer(
                  (norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer13): _DenseLayer(
                  (norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer14): _DenseLayer(
                  (norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer15): _DenseLayer(
                  (norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer16): _DenseLayer(
                  (norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer17): _DenseLayer(
                  (norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer18): _DenseLayer(
                  (norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer19): _DenseLayer(
                  (norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer20): _DenseLayer(
                  (norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer21): _DenseLayer(
                  (norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer22): _DenseLayer(
                  (norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer23): _DenseLayer(
                  (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer24): _DenseLayer(
                  (norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer25): _DenseLayer(
                  (norm1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1024, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer26): _DenseLayer(
                  (norm1): BatchNorm2d(1056, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1056, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer27): _DenseLayer(
                  (norm1): BatchNorm2d(1088, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1088, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer28): _DenseLayer(
                  (norm1): BatchNorm2d(1120, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1120, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer29): _DenseLayer(
                  (norm1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1152, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer30): _DenseLayer(
                  (norm1): BatchNorm2d(1184, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1184, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer31): _DenseLayer(
                  (norm1): BatchNorm2d(1216, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1216, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer32): _DenseLayer(
                  (norm1): BatchNorm2d(1248, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1248, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer33): _DenseLayer(
                  (norm1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1280, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer34): _DenseLayer(
                  (norm1): BatchNorm2d(1312, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1312, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer35): _DenseLayer(
                  (norm1): BatchNorm2d(1344, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1344, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer36): _DenseLayer(
                  (norm1): BatchNorm2d(1376, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1376, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer37): _DenseLayer(
                  (norm1): BatchNorm2d(1408, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1408, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer38): _DenseLayer(
                  (norm1): BatchNorm2d(1440, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1440, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer39): _DenseLayer(
                  (norm1): BatchNorm2d(1472, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1472, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer40): _DenseLayer(
                  (norm1): BatchNorm2d(1504, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1504, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer41): _DenseLayer(
                  (norm1): BatchNorm2d(1536, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1536, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer42): _DenseLayer(
                  (norm1): BatchNorm2d(1568, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1568, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer43): _DenseLayer(
                  (norm1): BatchNorm2d(1600, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1600, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer44): _DenseLayer(
                  (norm1): BatchNorm2d(1632, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1632, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer45): _DenseLayer(
                  (norm1): BatchNorm2d(1664, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1664, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer46): _DenseLayer(
                  (norm1): BatchNorm2d(1696, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1696, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer47): _DenseLayer(
                  (norm1): BatchNorm2d(1728, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1728, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer48): _DenseLayer(
                  (norm1): BatchNorm2d(1760, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1760, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
              )
              (transition3): _Transition(
                (norm): BatchNorm2d(1792, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
                (conv): Conv2d(1792, 896, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
              )
              (denseblock4): _DenseBlock(
                (denselayer1): _DenseLayer(
                  (norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer2): _DenseLayer(
                  (norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer3): _DenseLayer(
                  (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer4): _DenseLayer(
                  (norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer5): _DenseLayer(
                  (norm1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1024, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer6): _DenseLayer(
                  (norm1): BatchNorm2d(1056, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1056, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer7): _DenseLayer(
                  (norm1): BatchNorm2d(1088, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1088, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer8): _DenseLayer(
                  (norm1): BatchNorm2d(1120, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1120, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer9): _DenseLayer(
                  (norm1): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1152, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer10): _DenseLayer(
                  (norm1): BatchNorm2d(1184, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1184, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer11): _DenseLayer(
                  (norm1): BatchNorm2d(1216, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1216, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer12): _DenseLayer(
                  (norm1): BatchNorm2d(1248, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1248, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer13): _DenseLayer(
                  (norm1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1280, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer14): _DenseLayer(
                  (norm1): BatchNorm2d(1312, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1312, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer15): _DenseLayer(
                  (norm1): BatchNorm2d(1344, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1344, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer16): _DenseLayer(
                  (norm1): BatchNorm2d(1376, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1376, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer17): _DenseLayer(
                  (norm1): BatchNorm2d(1408, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1408, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer18): _DenseLayer(
                  (norm1): BatchNorm2d(1440, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1440, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer19): _DenseLayer(
                  (norm1): BatchNorm2d(1472, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1472, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer20): _DenseLayer(
                  (norm1): BatchNorm2d(1504, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1504, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer21): _DenseLayer(
                  (norm1): BatchNorm2d(1536, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1536, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer22): _DenseLayer(
                  (norm1): BatchNorm2d(1568, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1568, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer23): _DenseLayer(
                  (norm1): BatchNorm2d(1600, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1600, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer24): _DenseLayer(
                  (norm1): BatchNorm2d(1632, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1632, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer25): _DenseLayer(
                  (norm1): BatchNorm2d(1664, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1664, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer26): _DenseLayer(
                  (norm1): BatchNorm2d(1696, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1696, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer27): _DenseLayer(
                  (norm1): BatchNorm2d(1728, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1728, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer28): _DenseLayer(
                  (norm1): BatchNorm2d(1760, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1760, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer29): _DenseLayer(
                  (norm1): BatchNorm2d(1792, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1792, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer30): _DenseLayer(
                  (norm1): BatchNorm2d(1824, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1824, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer31): _DenseLayer(
                  (norm1): BatchNorm2d(1856, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1856, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
                (denselayer32): _DenseLayer(
                  (norm1): BatchNorm2d(1888, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu1): ReLU(inplace=True)
                  (conv1): Conv2d(1888, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                  (relu2): ReLU(inplace=True)
                  (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                )
              )
              (norm5): BatchNorm2d(1920, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
            (classifier): Linear(in_features=1920, out_features=1000, bias=True)
          )
        )
      )
      (saliency_networks): ModuleList(
        (0): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (1): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (2): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (3): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (4): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (5): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (6): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (7): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (8): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (9): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (10): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (11): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (12): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (13): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (14): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (15): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (16): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (17): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (18): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (19): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (20): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (21): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (22): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (23): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (24): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (25): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (26): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (27): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (28): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (29): Sequential(
          (layernorm0): LayerNorm(2048, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2048, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
      )
      (scanpath_networks): ModuleList(
        (0): None
        (1): None
        (2): None
        (3): None
        (4): None
        (5): None
        (6): None
        (7): None
        (8): None
        (9): None
        (10): None
        (11): None
        (12): None
        (13): None
        (14): None
        (15): None
        (16): None
        (17): None
        (18): None
        (19): None
        (20): None
        (21): None
        (22): None
        (23): None
        (24): None
        (25): None
        (26): None
        (27): None
        (28): None
        (29): None
      )
      (fixation_selection_networks): ModuleList(
        (0): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (1): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (2): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (3): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (4): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (5): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (6): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (7): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (8): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (9): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (10): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (11): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (12): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (13): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (14): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (15): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (16): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (17): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (18): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (19): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (20): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (21): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (22): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (23): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (24): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (25): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (26): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (27): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (28): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (29): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
      )
      (finalizers): ModuleList(
        (0): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (1): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (2): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (3): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (4): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (5): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (6): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (7): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (8): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (9): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (10): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (11): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (12): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (13): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (14): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (15): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (16): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (17): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (18): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (19): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (20): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (21): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (22): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (23): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (24): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (25): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (26): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (27): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (28): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (29): Finalizer(
          (gauss): GaussianFilterNd()
        )
      )
    )
    (3): DeepGazeIIIMixture(
      (features): FeatureExtractor(
        (features): RGBResNext50(
          (0): Normalizer()
          (1): ResNet(
            (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
            (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (relu): ReLU(inplace=True)
            (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
            (layer1): Sequential(
              (0): Bottleneck(
                (conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
                (downsample): Sequential(
                  (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                  (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                )
              )
              (1): Bottleneck(
                (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
              (2): Bottleneck(
                (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
            )
            (layer2): Sequential(
              (0): Bottleneck(
                (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
                (downsample): Sequential(
                  (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
                  (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                )
              )
              (1): Bottleneck(
                (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
              (2): Bottleneck(
                (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
              (3): Bottleneck(
                (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
            )
            (layer3): Sequential(
              (0): Bottleneck(
                (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
                (downsample): Sequential(
                  (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
                  (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                )
              )
              (1): Bottleneck(
                (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
              (2): Bottleneck(
                (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
              (3): Bottleneck(
                (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
              (4): Bottleneck(
                (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
              (5): Bottleneck(
                (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
            )
            (layer4): Sequential(
              (0): Bottleneck(
                (conv1): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
                (downsample): Sequential(
                  (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
                  (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                )
              )
              (1): Bottleneck(
                (conv1): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
              (2): Bottleneck(
                (conv1): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv2): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
                (bn2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (conv3): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu): ReLU(inplace=True)
              )
            )
            (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
            (fc): Linear(in_features=2048, out_features=1000, bias=True)
          )
        )
      )
      (saliency_networks): ModuleList(
        (0): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (1): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (2): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (3): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (4): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (5): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (6): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (7): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (8): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (9): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (10): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (11): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (12): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (13): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (14): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (15): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (16): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (17): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (18): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (19): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (20): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (21): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (22): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (23): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (24): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (25): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (26): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (27): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (28): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
        (29): Sequential(
          (layernorm0): LayerNorm(2560, eps=1e-12, center=True, scale=True)
          (conv0): Conv2d(2560, 8, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias0): Bias(channels=8)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(8, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (layernorm2): LayerNorm(16, eps=1e-12, center=True, scale=True)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias2): Bias(channels=1)
          (softplus3): Softplus(beta=1, threshold=20)
        )
      )
      (scanpath_networks): ModuleList(
        (0): None
        (1): None
        (2): None
        (3): None
        (4): None
        (5): None
        (6): None
        (7): None
        (8): None
        (9): None
        (10): None
        (11): None
        (12): None
        (13): None
        (14): None
        (15): None
        (16): None
        (17): None
        (18): None
        (19): None
        (20): None
        (21): None
        (22): None
        (23): None
        (24): None
        (25): None
        (26): None
        (27): None
        (28): None
        (29): None
      )
      (fixation_selection_networks): ModuleList(
        (0): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (1): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (2): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (3): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (4): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (5): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (6): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (7): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (8): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (9): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (10): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (11): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (12): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (13): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (14): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (15): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (16): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (17): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (18): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (19): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (20): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (21): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (22): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (23): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (24): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (25): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (26): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (27): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (28): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
        (29): Sequential(
          (layernorm0): LayerNormMultiInput(
            (layernorm_part0): LayerNorm(1, eps=1e-12, center=True, scale=True)
          )
          (conv0): Conv2dMultiInput(
            (conv_part0): Conv2d(1, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          )
          (bias0): Bias(channels=128)
          (softplus0): Softplus(beta=1, threshold=20)
          (layernorm1): LayerNorm(128, eps=1e-12, center=True, scale=True)
          (conv1): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bias1): Bias(channels=16)
          (softplus1): Softplus(beta=1, threshold=20)
          (conv2): Conv2d(16, 1, kernel_size=(1, 1), stride=(1, 1), bias=False)
        )
      )
      (finalizers): ModuleList(
        (0): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (1): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (2): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (3): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (4): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (5): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (6): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (7): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (8): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (9): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (10): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (11): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (12): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (13): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (14): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (15): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (16): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (17): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (18): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (19): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (20): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (21): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (22): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (23): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (24): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (25): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (26): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (27): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (28): Finalizer(
          (gauss): GaussianFilterNd()
        )
        (29): Finalizer(
          (gauss): GaussianFilterNd()
        )
      )
    )
  )
)