2024/01/18 13:41:34 - mmengine - INFO - 
------------------------------------------------------------
System environment:
    sys.platform: linux
    Python: 3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]
    CUDA available: True
    numpy_random_seed: 1142582054
    GPU 0,1,2,3,4,5,6: NVIDIA A100-SXM4-80GB
    CUDA_HOME: /usr/local/cuda-11.7
    NVCC: Cuda compilation tools, release 11.7, V11.7.64
    GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.3) 9.4.0
    PyTorch: 1.13.0
    PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201402
  - Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.7
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
  - CuDNN 8.5
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

    TorchVision: 0.14.0
    OpenCV: 4.8.1
    MMEngine: 0.10.1

Runtime environment:
    cudnn_benchmark: True
    mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
    dist_cfg: {'backend': 'nccl'}
    seed: 1142582054
    Distributed launcher: pytorch
    Distributed training: True
    GPU number: 4
------------------------------------------------------------

2024/01/18 13:41:36 - mmengine - INFO - Config:
backbone_norm_cfg = dict(requires_grad=True, type='LN')
checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_small_patch4_window7_224_20220317-7ba6d6dd.pth'
crop_size = (
    640,
    640,
)
data_preprocessor = dict(
    bgr_to_rgb=True,
    mean=[
        123.675,
        116.28,
        103.53,
    ],
    pad_val=0,
    seg_pad_val=255,
    size=(
        640,
        640,
    ),
    std=[
        58.395,
        57.12,
        57.375,
    ],
    type='SegDataPreProcessor')
data_root = 'data/ade/ADEChallengeData2016'
dataset_type = 'ADE20KDataset'
default_hooks = dict(
    checkpoint=dict(by_epoch=False, interval=16000, type='CheckpointHook'),
    logger=dict(interval=50, log_metric_by_epoch=False, type='LoggerHook'),
    param_scheduler=dict(type='ParamSchedulerHook'),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    timer=dict(type='IterTimerHook'),
    visualization=dict(type='SegVisualizationHook'))
default_scope = 'mmseg'
env_cfg = dict(
    cudnn_benchmark=True,
    dist_cfg=dict(backend='nccl'),
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
img_ratios = [
    0.5,
    0.75,
    1.0,
    1.25,
    1.5,
    1.75,
]
launcher = 'pytorch'
load_from = '/home/LiuYue/Workspace3/ckpts/segmentation/work_dirs/upernet_vssm_4xb4-160k_ade20k-640x640_small/iter_160000.pth'
log_level = 'INFO'
log_processor = dict(by_epoch=False)
model = dict(
    module=dict(
        auxiliary_head=dict(
            align_corners=False,
            channels=256,
            concat_input=False,
            dropout_ratio=0.1,
            in_channels=384,
            in_index=2,
            loss_decode=dict(
                loss_weight=0.4, type='CrossEntropyLoss', use_sigmoid=False),
            norm_cfg=dict(requires_grad=True, type='SyncBN'),
            num_classes=150,
            num_convs=1,
            type='FCNHead'),
        backbone=dict(
            act_cfg=dict(type='GELU'),
            attn_drop_rate=0.0,
            depths=(
                2,
                2,
                27,
                2,
            ),
            dims=96,
            drop_path_rate=0.3,
            drop_rate=0.0,
            embed_dims=96,
            init_cfg=dict(
                checkpoint=
                'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_small_patch4_window7_224_20220317-7ba6d6dd.pth',
                type='Pretrained'),
            mlp_ratio=4,
            norm_cfg=dict(requires_grad=True, type='LN'),
            num_heads=[
                3,
                6,
                12,
                24,
            ],
            out_indices=(
                0,
                1,
                2,
                3,
            ),
            patch_norm=True,
            patch_size=4,
            pretrain_img_size=224,
            pretrained='../../ckpts/vssmsmall/ckpt_epoch_238.pth',
            qk_scale=None,
            qkv_bias=True,
            strides=(
                4,
                2,
                2,
                2,
            ),
            type='MMSEG_VSSM',
            use_abs_pos_embed=False,
            window_size=7),
        data_preprocessor=dict(
            bgr_to_rgb=True,
            mean=[
                123.675,
                116.28,
                103.53,
            ],
            pad_val=0,
            seg_pad_val=255,
            size=(
                640,
                640,
            ),
            std=[
                58.395,
                57.12,
                57.375,
            ],
            type='SegDataPreProcessor'),
        decode_head=dict(
            align_corners=False,
            channels=512,
            dropout_ratio=0.1,
            in_channels=[
                96,
                192,
                384,
                768,
            ],
            in_index=[
                0,
                1,
                2,
                3,
            ],
            loss_decode=dict(
                loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False),
            norm_cfg=dict(requires_grad=True, type='SyncBN'),
            num_classes=150,
            pool_scales=(
                1,
                2,
                3,
                6,
            ),
            type='UPerHead'),
        pretrained=None,
        test_cfg=dict(mode='whole'),
        train_cfg=dict(),
        type='EncoderDecoder'),
    type='SegTTAModel')
norm_cfg = dict(requires_grad=True, type='SyncBN')
optim_wrapper = dict(
    optimizer=dict(
        betas=(
            0.9,
            0.999,
        ), lr=6e-05, type='AdamW', weight_decay=0.01),
    paramwise_cfg=dict(
        custom_keys=dict(
            absolute_pos_embed=dict(decay_mult=0.0),
            norm=dict(decay_mult=0.0),
            relative_position_bias_table=dict(decay_mult=0.0))),
    type='OptimWrapper')
optimizer = dict(lr=0.01, momentum=0.9, type='SGD', weight_decay=0.0005)
param_scheduler = [
    dict(
        begin=0, by_epoch=False, end=1500, start_factor=1e-06,
        type='LinearLR'),
    dict(
        begin=1500,
        by_epoch=False,
        end=160000,
        eta_min=0.0,
        power=1.0,
        type='PolyLR'),
]
resume = False
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
    batch_size=1,
    dataset=dict(
        data_prefix=dict(
            img_path='images/validation',
            seg_map_path='annotations/validation'),
        data_root='data/ade/ADEChallengeData2016',
        pipeline=[
            dict(backend_args=None, type='LoadImageFromFile'),
            dict(
                transforms=[
                    [
                        dict(keep_ratio=True, scale_factor=0.5, type='Resize'),
                        dict(
                            keep_ratio=True, scale_factor=0.75, type='Resize'),
                        dict(keep_ratio=True, scale_factor=1.0, type='Resize'),
                        dict(
                            keep_ratio=True, scale_factor=1.25, type='Resize'),
                        dict(keep_ratio=True, scale_factor=1.5, type='Resize'),
                        dict(
                            keep_ratio=True, scale_factor=1.75, type='Resize'),
                    ],
                    [
                        dict(
                            direction='horizontal',
                            prob=0.0,
                            type='RandomFlip'),
                        dict(
                            direction='horizontal',
                            prob=1.0,
                            type='RandomFlip'),
                    ],
                    [
                        dict(type='LoadAnnotations'),
                    ],
                    [
                        dict(type='PackSegInputs'),
                    ],
                ],
                type='TestTimeAug'),
        ],
        type='ADE20KDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
    iou_metrics=[
        'mIoU',
    ], type='IoUMetric')
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(keep_ratio=True, scale=(
        2560,
        640,
    ), type='Resize'),
    dict(reduce_zero_label=True, type='LoadAnnotations'),
    dict(type='PackSegInputs'),
]
train_cfg = dict(
    max_iters=160000, type='IterBasedTrainLoop', val_interval=16000)
train_dataloader = dict(
    batch_size=2,
    dataset=dict(
        data_prefix=dict(
            img_path='images/training', seg_map_path='annotations/training'),
        data_root='data/ade/ADEChallengeData2016',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(reduce_zero_label=True, type='LoadAnnotations'),
            dict(
                keep_ratio=True,
                ratio_range=(
                    0.5,
                    2.0,
                ),
                scale=(
                    2560,
                    640,
                ),
                type='RandomResize'),
            dict(
                cat_max_ratio=0.75, crop_size=(
                    640,
                    640,
                ), type='RandomCrop'),
            dict(prob=0.5, type='RandomFlip'),
            dict(type='PhotoMetricDistortion'),
            dict(type='PackSegInputs'),
        ],
        type='ADE20KDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=True, type='InfiniteSampler'))
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(reduce_zero_label=True, type='LoadAnnotations'),
    dict(
        keep_ratio=True,
        ratio_range=(
            0.5,
            2.0,
        ),
        scale=(
            2560,
            640,
        ),
        type='RandomResize'),
    dict(cat_max_ratio=0.75, crop_size=(
        640,
        640,
    ), type='RandomCrop'),
    dict(prob=0.5, type='RandomFlip'),
    dict(type='PhotoMetricDistortion'),
    dict(type='PackSegInputs'),
]
tta_model = dict(
    module=dict(
        auxiliary_head=dict(
            align_corners=False,
            channels=256,
            concat_input=False,
            dropout_ratio=0.1,
            in_channels=384,
            in_index=2,
            loss_decode=dict(
                loss_weight=0.4, type='CrossEntropyLoss', use_sigmoid=False),
            norm_cfg=dict(requires_grad=True, type='SyncBN'),
            num_classes=150,
            num_convs=1,
            type='FCNHead'),
        backbone=dict(
            act_cfg=dict(type='GELU'),
            attn_drop_rate=0.0,
            depths=(
                2,
                2,
                27,
                2,
            ),
            dims=96,
            drop_path_rate=0.3,
            drop_rate=0.0,
            embed_dims=96,
            init_cfg=dict(
                checkpoint=
                'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_small_patch4_window7_224_20220317-7ba6d6dd.pth',
                type='Pretrained'),
            mlp_ratio=4,
            norm_cfg=dict(requires_grad=True, type='LN'),
            num_heads=[
                3,
                6,
                12,
                24,
            ],
            out_indices=(
                0,
                1,
                2,
                3,
            ),
            patch_norm=True,
            patch_size=4,
            pretrain_img_size=224,
            pretrained='../../ckpts/vssmsmall/ckpt_epoch_238.pth',
            qk_scale=None,
            qkv_bias=True,
            strides=(
                4,
                2,
                2,
                2,
            ),
            type='MMSEG_VSSM',
            use_abs_pos_embed=False,
            window_size=7),
        data_preprocessor=dict(
            bgr_to_rgb=True,
            mean=[
                123.675,
                116.28,
                103.53,
            ],
            pad_val=0,
            seg_pad_val=255,
            size=(
                640,
                640,
            ),
            std=[
                58.395,
                57.12,
                57.375,
            ],
            type='SegDataPreProcessor'),
        decode_head=dict(
            align_corners=False,
            channels=512,
            dropout_ratio=0.1,
            in_channels=[
                96,
                192,
                384,
                768,
            ],
            in_index=[
                0,
                1,
                2,
                3,
            ],
            loss_decode=dict(
                loss_weight=1.0, type='CrossEntropyLoss', use_sigmoid=False),
            norm_cfg=dict(requires_grad=True, type='SyncBN'),
            num_classes=150,
            pool_scales=(
                1,
                2,
                3,
                6,
            ),
            type='UPerHead'),
        pretrained=None,
        test_cfg=dict(mode='whole'),
        train_cfg=dict(),
        type='EncoderDecoder'),
    type='SegTTAModel')
tta_pipeline = [
    dict(backend_args=None, type='LoadImageFromFile'),
    dict(
        transforms=[
            [
                dict(keep_ratio=True, scale_factor=0.5, type='Resize'),
                dict(keep_ratio=True, scale_factor=0.75, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.0, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.25, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.5, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.75, type='Resize'),
            ],
            [
                dict(direction='horizontal', prob=0.0, type='RandomFlip'),
                dict(direction='horizontal', prob=1.0, type='RandomFlip'),
            ],
            [
                dict(type='LoadAnnotations'),
            ],
            [
                dict(type='PackSegInputs'),
            ],
        ],
        type='TestTimeAug'),
]
val_cfg = dict(type='ValLoop')
val_dataloader = dict(
    batch_size=1,
    dataset=dict(
        data_prefix=dict(
            img_path='images/validation',
            seg_map_path='annotations/validation'),
        data_root='data/ade/ADEChallengeData2016',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                2560,
                640,
            ), type='Resize'),
            dict(reduce_zero_label=True, type='LoadAnnotations'),
            dict(type='PackSegInputs'),
        ],
        type='ADE20KDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
val_evaluator = dict(
    iou_metrics=[
        'mIoU',
    ], type='IoUMetric')
vis_backends = [
    dict(type='LocalVisBackend'),
]
visualizer = dict(
    name='visualizer',
    type='SegLocalVisualizer',
    vis_backends=[
        dict(type='LocalVisBackend'),
    ])
work_dir = './work_dirs/upernet_vssm_4xb4-160k_ade20k-640x640_small'

2024/01/18 13:41:39 - mmengine - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) RuntimeInfoHook                    
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
before_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_train_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) DistSamplerSeedHook                
 -------------------- 
before_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_train_epoch:
(NORMAL      ) IterTimerHook                      
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_val_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_val_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_val_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_val_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_val:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
before_test_epoch:
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_test_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_test_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) SegVisualizationHook               
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test:
(VERY_HIGH   ) RuntimeInfoHook                    
 -------------------- 
after_run:
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
2024/01/18 13:41:41 - mmengine - WARNING - The prefix is not set in metric class IoUMetric.
2024/01/18 13:41:42 - mmengine - INFO - Load checkpoint from /home/LiuYue/Workspace3/ckpts/segmentation/work_dirs/upernet_vssm_4xb4-160k_ade20k-640x640_small/iter_160000.pth
2024/01/18 13:53:00 - mmengine - INFO - Iter(test) [ 50/500]    eta: 1:41:38  time: 9.2342  data_time: 0.0153  memory: 53982  
2024/01/18 14:00:40 - mmengine - INFO - Iter(test) [100/500]    eta: 1:15:51  time: 3.6223  data_time: 0.0136  memory: 52867  
2024/01/18 14:04:27 - mmengine - INFO - Iter(test) [150/500]    eta: 0:53:03  time: 1.3106  data_time: 0.0160  memory: 52745  
2024/01/18 14:11:51 - mmengine - INFO - Iter(test) [200/500]    eta: 0:45:12  time: 3.2742  data_time: 0.0150  memory: 52971  
2024/01/18 14:15:23 - mmengine - INFO - Iter(test) [250/500]    eta: 0:33:40  time: 4.4249  data_time: 0.0168  memory: 53191  
2024/01/18 14:20:45 - mmengine - INFO - Iter(test) [300/500]    eta: 0:26:01  time: 6.0236  data_time: 0.0202  memory: 56580  
2024/01/18 14:24:59 - mmengine - INFO - Iter(test) [350/500]    eta: 0:18:32  time: 7.2593  data_time: 0.0146  memory: 52298  
2024/01/18 14:28:39 - mmengine - INFO - Iter(test) [400/500]    eta: 0:11:44  time: 2.0090  data_time: 0.0136  memory: 53112  
2024/01/18 14:32:55 - mmengine - INFO - Iter(test) [450/500]    eta: 0:05:41  time: 0.9588  data_time: 0.0158  memory: 52817  
2024/01/18 14:36:26 - mmengine - INFO - Iter(test) [500/500]    eta: 0:00:00  time: 7.8064  data_time: 0.0142  memory: 52995  
2024/01/18 14:38:02 - mmengine - INFO - per class results:
2024/01/18 14:38:02 - mmengine - INFO - 
+---------------------+-------+-------+
|        Class        |  IoU  |  Acc  |
+---------------------+-------+-------+
|         wall        | 78.75 | 89.36 |
|       building      | 83.12 | 92.71 |
|         sky         |  94.5 | 97.63 |
|        floor        | 81.76 | 90.23 |
|         tree        | 74.85 | 88.04 |
|       ceiling       | 85.58 | 92.92 |
|         road        | 85.53 | 91.16 |
|         bed         | 89.56 | 95.86 |
|      windowpane     | 64.66 | 81.12 |
|        grass        | 65.41 | 80.54 |
|       cabinet       | 61.71 | 73.16 |
|       sidewalk      | 69.77 | 82.53 |
|        person       | 80.78 | 92.72 |
|        earth        | 39.83 | 53.66 |
|         door        | 53.67 | 67.04 |
|        table        | 61.54 | 79.57 |
|       mountain      | 57.79 | 75.02 |
|        plant        |  52.7 | 63.35 |
|       curtain       | 74.79 | 86.97 |
|        chair        | 59.42 | 72.69 |
|         car         | 84.32 | 92.36 |
|        water        | 55.89 |  69.4 |
|       painting      | 74.79 |  87.5 |
|         sofa        | 68.36 | 84.71 |
|        shelf        | 44.36 |  63.6 |
|        house        | 46.15 | 61.18 |
|         sea         | 57.85 | 81.06 |
|        mirror       | 69.21 | 77.51 |
|         rug         | 61.87 | 73.64 |
|        field        | 29.81 | 47.44 |
|       armchair      | 46.69 | 64.08 |
|         seat        | 62.14 | 82.15 |
|        fence        | 47.03 |  64.8 |
|         desk        | 53.19 | 70.23 |
|         rock        |  46.6 | 70.86 |
|       wardrobe      | 46.65 | 66.04 |
|         lamp        | 66.87 | 78.03 |
|       bathtub       | 83.11 | 86.64 |
|       railing       | 35.37 |  49.1 |
|       cushion       | 60.08 | 72.91 |
|         base        | 28.85 | 42.24 |
|         box         | 26.91 | 33.36 |
|        column       | 46.47 | 58.22 |
|      signboard      | 38.24 | 51.08 |
|   chest of drawers  |  45.6 | 66.14 |
|       counter       | 25.59 | 34.04 |
|         sand        | 45.36 | 64.69 |
|         sink        |  73.4 | 81.15 |
|      skyscraper     | 49.52 | 60.23 |
|      fireplace      | 80.08 | 90.52 |
|     refrigerator    | 76.78 | 81.87 |
|      grandstand     | 46.64 | 79.47 |
|         path        | 25.75 | 36.79 |
|        stairs       | 34.91 | 44.92 |
|        runway       | 70.95 |  92.5 |
|         case        | 61.74 | 76.13 |
|      pool table     | 91.83 | 96.65 |
|        pillow       | 60.23 | 71.02 |
|     screen door     | 70.03 | 75.59 |
|       stairway      | 34.92 | 41.71 |
|        river        |  9.03 | 17.44 |
|        bridge       | 67.13 | 78.16 |
|       bookcase      | 44.09 |  68.9 |
|        blind        | 46.02 | 50.39 |
|     coffee table    | 59.14 | 82.97 |
|        toilet       | 85.59 | 90.78 |
|        flower       | 37.12 | 51.46 |
|         book        | 46.03 | 62.65 |
|         hill        |  12.8 | 20.47 |
|        bench        | 40.19 | 46.67 |
|      countertop     | 56.79 | 74.35 |
|        stove        | 78.19 | 85.06 |
|         palm        | 51.92 | 70.76 |
|    kitchen island   | 49.25 | 77.56 |
|       computer      | 76.69 | 89.25 |
|     swivel chair    | 46.97 | 64.54 |
|         boat        | 39.55 | 56.75 |
|         bar         | 40.71 | 53.86 |
|    arcade machine   | 85.72 | 94.08 |
|        hovel        | 33.09 |  39.0 |
|         bus         | 93.28 | 97.04 |
|        towel        | 66.95 | 78.09 |
|        light        | 57.36 | 64.37 |
|        truck        | 43.92 |  56.1 |
|        tower        | 17.34 | 27.06 |
|      chandelier     | 70.27 | 85.27 |
|        awning       | 25.15 | 30.83 |
|     streetlight     | 27.76 | 33.84 |
|        booth        | 34.47 | 38.09 |
| television receiver | 70.57 | 77.57 |
|       airplane      | 60.13 | 67.32 |
|      dirt track     |  1.29 |  2.65 |
|       apparel       | 30.46 | 48.93 |
|         pole        | 22.16 | 29.32 |
|         land        |  2.43 |  3.38 |
|      bannister      | 12.98 | 17.41 |
|      escalator      | 35.52 | 51.31 |
|       ottoman       | 49.75 |  64.2 |
|        bottle       | 36.52 | 57.03 |
|        buffet       | 45.18 | 59.91 |
|        poster       | 26.96 | 30.14 |
|        stage        | 15.07 | 19.98 |
|         van         | 40.79 | 58.46 |
|         ship        | 58.61 |  93.2 |
|       fountain      | 37.13 | 37.62 |
|    conveyer belt    | 73.14 | 91.11 |
|        canopy       | 16.41 | 21.48 |
|        washer       | 70.64 | 72.56 |
|      plaything      | 26.95 | 40.15 |
|    swimming pool    | 46.85 | 49.67 |
|        stool        | 43.95 | 55.94 |
|        barrel       | 43.46 | 68.28 |
|        basket       | 28.25 | 40.89 |
|      waterfall      | 52.45 | 64.56 |
|         tent        | 88.84 | 98.38 |
|         bag         | 16.38 | 20.77 |
|       minibike      | 74.94 | 87.17 |
|        cradle       | 76.09 | 97.44 |
|         oven        | 56.13 |  67.6 |
|         ball        | 48.07 | 61.55 |
|         food        | 47.43 | 54.79 |
|         step        | 11.71 | 13.34 |
|         tank        | 49.12 | 52.75 |
|      trade name     | 25.88 | 29.71 |
|      microwave      | 85.51 | 93.72 |
|         pot         | 45.76 | 52.34 |
|        animal       | 55.15 |  57.0 |
|       bicycle       | 57.35 | 80.39 |
|         lake        |  47.5 | 63.73 |
|      dishwasher     | 70.78 | 80.28 |
|        screen       | 66.71 | 81.93 |
|       blanket       |  11.9 | 13.84 |
|      sculpture      | 64.88 | 77.88 |
|         hood        | 58.27 | 69.63 |
|        sconce       | 49.96 | 61.09 |
|         vase        |  44.7 |  55.6 |
|    traffic light    | 37.16 | 53.95 |
|         tray        |  7.6  | 10.69 |
|        ashcan       | 42.42 | 56.09 |
|         fan         | 62.16 | 76.81 |
|         pier        | 47.99 | 56.02 |
|      crt screen     |  6.95 |  19.0 |
|        plate        | 53.63 |  67.7 |
|       monitor       |  4.75 |  5.08 |
|    bulletin board   | 54.16 | 62.52 |
|        shower       |  0.0  |  0.0  |
|       radiator      | 62.46 | 71.64 |
|        glass        | 13.45 | 14.01 |
|        clock        |  40.9 | 46.31 |
|         flag        | 50.72 |  53.6 |
+---------------------+-------+-------+
2024/01/18 14:38:02 - mmengine - INFO - Iter(test) [500/500]    aAcc: 83.8800  mIoU: 50.7800  mAcc: 62.2700  data_time: 0.0226  time: 6.5675