IIR-Lab/models/archs/NAF_arch.py

import torch
import torch.nn as nn
# from basicsr.models.archs import recons_video81 as recons_video
# from basicsr.models.archs import flow_pwc82 as flow_pwc
import numpy as np
from torch.nn import functional as F
import torch.utils.checkpoint as checkpoint
from torch.cuda.amp import autocast as autocast
# from .StudentImage_arch import StudentImage
from torch.nn.parallel import DistributedDataParallel
from collections import OrderedDict
from .arch_util import DCNv2Pack
from .common import ResList

class LayerNormFunction(torch.autograd.Function):

    @staticmethod
    def forward(ctx, x, weight, bias, eps):
        ctx.eps = eps
        N, C, H, W = x.size()
        mu = x.mean(1, keepdim=True)
        var = (x - mu).pow(2).mean(1, keepdim=True)
        y = (x - mu) / (var + eps).sqrt()
        ctx.save_for_backward(y, var, weight)
        y = weight.view(1, C, 1, 1) * y + bias.view(1, C, 1, 1)
        return y

    @staticmethod
    def backward(ctx, grad_output):
        eps = ctx.eps

        N, C, H, W = grad_output.size()
        y, var, weight = ctx.saved_variables
        g = grad_output * weight.view(1, C, 1, 1)
        mean_g = g.mean(dim=1, keepdim=True)

        mean_gy = (g * y).mean(dim=1, keepdim=True)
        gx = 1. / torch.sqrt(var + eps) * (g - y * mean_gy - mean_g)
        return gx, (grad_output * y).sum(dim=3).sum(dim=2).sum(dim=0), grad_output.sum(dim=3).sum(dim=2).sum(
            dim=0), None


class LayerNorm2d(nn.Module):

    def __init__(self, channels, eps=1e-6):
        super(LayerNorm2d, self).__init__()
        self.register_parameter('weight', nn.Parameter(torch.ones(channels)))
        self.register_parameter('bias', nn.Parameter(torch.zeros(channels)))
        self.eps = eps

    def forward(self, x):
        return LayerNormFunction.apply(x, self.weight, self.bias, self.eps)

class SimpleGate(nn.Module):
    def forward(self, x):
        x1, x2 = x.chunk(2, dim=1)
        return x1 * x2

class NAFBlock(nn.Module):
    def __init__(self, c, DW_Expand=2, FFN_Expand=2, drop_out_rate=0.):
        super().__init__()
        dw_channel = c * DW_Expand
        self.conv1 = nn.Conv2d(in_channels=c, out_channels=dw_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
        self.conv2 = nn.Conv2d(in_channels=dw_channel, out_channels=dw_channel, kernel_size=3, padding=1, stride=1, groups=dw_channel,
                               bias=True)
        self.conv3 = nn.Conv2d(in_channels=dw_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
        
        # Simplified Channel Attention
        self.sca = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(in_channels=dw_channel // 2, out_channels=dw_channel // 2, kernel_size=1, padding=0, stride=1,
                      groups=1, bias=True),
        )

        # SimpleGate
        self.sg = SimpleGate()

        ffn_channel = FFN_Expand * c
        self.conv4 = nn.Conv2d(in_channels=c, out_channels=ffn_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
        self.conv5 = nn.Conv2d(in_channels=ffn_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True)

        self.norm1 = LayerNorm2d(c)
        self.norm2 = LayerNorm2d(c)

        self.dropout1 = nn.Dropout(drop_out_rate) if drop_out_rate > 0. else nn.Identity()
        self.dropout2 = nn.Dropout(drop_out_rate) if drop_out_rate > 0. else nn.Identity()

        self.beta = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
        self.gamma = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)

    def forward(self, inp):
        x = inp

        x = self.norm1(x)

        x = self.conv1(x)
        x = self.conv2(x)
        x = self.sg(x)
        x = x * self.sca(x)
        x = self.conv3(x)

        x = self.dropout1(x)

        y = inp + x * self.beta

        x = self.conv4(self.norm2(y))
        x = self.sg(x)
        x = self.conv5(x)

        x = self.dropout2(x)

        return y + x * self.gamma


class NAF_Video(nn.Module):

    def __init__(self,args, img_channel=4, width=64, middle_blk_num=12, enc_blk_nums=[2, 2, 4, 8], dec_blk_nums=[2, 2, 2, 2]):
        super().__init__()

        self.lrelu = nn.LeakyReLU(0.2)
        self.convfist = nn.Conv2d(4, 64, 3, 1, 1)
        self.feature_extraction = ResList(5, 64)

        self.ending = nn.Conv2d(in_channels=width, out_channels=4, kernel_size=3, padding=1, stride=1, groups=1,
                              bias=True)

        self.encoders = nn.ModuleList()
        self.decoders = nn.ModuleList()
        self.middle_blks = nn.ModuleList()
        self.ups = nn.ModuleList()
        self.downs = nn.ModuleList()

        chan = width
        for num in enc_blk_nums:
            self.encoders.append(
                nn.Sequential(
                    *[NAFBlock(chan) for _ in range(num)]
                )
            )
            self.downs.append(
                nn.Conv2d(chan, 2*chan, 2, 2)
            )
            chan = chan * 2

        self.middle_blks = \
            nn.Sequential(
                *[NAFBlock(chan) for _ in range(middle_blk_num)]
            )

        for num in dec_blk_nums:
            self.ups.append(
                nn.Sequential(
                    nn.Conv2d(chan, chan * 2, 1, bias=False),
                    nn.PixelShuffle(2)
                )
            )
            chan = chan // 2
            self.decoders.append(
                nn.Sequential(
                    *[NAFBlock(chan) for _ in range(num)]
                )
            )

        self.padder_size = 2 ** len(self.encoders)   # 16

    def forward(self, x):
       
        center = x
   
        x = self.lrelu(self.convfist(x))
        x = self.feature_extraction(x)

        encs = []


        for encoder, down in zip(self.encoders, self.downs):
            x = encoder(x)
            encs.append(x)
            x = down(x)

        x = self.middle_blks(x)

          
        for decoder, up, enc_skip in zip(self.decoders, self.ups, encs[::-1]):
            x = up(x)
            x = x + enc_skip
            x = decoder(x)

        x = self.ending(x)
        
        x = x + center

        return x

 
def load_networks(network, resume, strict=True):
    load_path = resume

    if isinstance(network, nn.DataParallel) or isinstance(network, DistributedDataParallel): #会带有.module
        network = network.module     #可以当前net的把.module 去掉 
    load_net = torch.load(load_path, map_location=torch.device('cuda'))
    load_net_clean = OrderedDict()  # remove unnecessary 'module.'
    for k, v in load_net.items():  #可以把加载的net的把.module 去掉 
        if k.startswith('module.'):
            load_net_clean[k[7:]] = v
        else:
            load_net_clean[k] = v

    network.load_state_dict(load_net_clean, strict=True)