定义、提取网络、.modules()、.children()

class VGG19_Extractor_assigned(nn.Module):
    def __init__(self, output_layer_list=[2, 7, 16, 25]):  #
        super(VGG19_Extractor_assigned, self).__init__()

        self.vgg19=models.vgg19(pretrained=True)
        self.vgg_features = self.vgg19.features
        self.vgglist=list(self.vgg_features.modules())
        self.module_list = self.vgglist[1:]
        print(self.vgg19)
        print('--------------------')

        for id,mo in enumerate(self.vgglist):
            print(id,mo)
        self.output_layer_list = output_layer_list
        self.mean = nn.Parameter(torch.Tensor([0.485, 0.456, 0.406]).view(1, 3, 1, 1), requires_grad=False)
        self.std = nn.Parameter(torch.Tensor([0.229, 0.224, 0.225]).view(1, 3, 1, 1), requires_grad=False)

    def forward(self, x):
        # print('shpe',x.shape,self.mean.repeat(x.size(0),1,x.size(2),x.size(3)).shape)
        x = x - self.mean.repeat(x.size(0), 1, x.size(2), x.size(3))
        x = x / self.std.repeat(x.size(0), 1, x.size(2), x.size(3))
        output_list = []
        for module_idx, module in enumerate(self.module_list):

            x = module(x)
            # print('vgg',module_idx,x.shape) #0-36
            if module_idx in self.output_layer_list:  # module_idx in output_layer_list:#self.output_layer_list:
                output_list.append(x)
        return output_list

定义vgg19网络main函数

input_tensor = torch.ones([1, 3, 64, 64], dtype=torch.float32)
    #vgg19_extractor_assigned = Resnet18_Extractor_assigned2(output_layer_list=[3, 8, 17, 26])
vgg19_extractor_assigned = VGG19_Extractor_assigned(output_layer_list=[3, 8, 17, 26])

out=vgg19_extractor_assigned(input_tensor)

vgg19网络结构为（print(self.vgg19)的输出）

VGG(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU(inplace=True)
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU(inplace=True)
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU(inplace=True)
    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU(inplace=True)
    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace=True)
    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU(inplace=True)
    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU(inplace=True)
    (16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (17): ReLU(inplace=True)
    (18): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (19): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU(inplace=True)
    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU(inplace=True)
    (23): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (24): ReLU(inplace=True)
    (25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (26): ReLU(inplace=True)
    (27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU(inplace=True)
    (30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (31): ReLU(inplace=True)
    (32): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (33): ReLU(inplace=True)
    (34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (35): ReLU(inplace=True)
    (36): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
  (classifier): Sequential(
    (0): Linear(in_features=25088, out_features=4096, bias=True)
    (1): ReLU(inplace=True)
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=4096, out_features=4096, bias=True)
    (4): ReLU(inplace=True)
    (5): Dropout(p=0.5, inplace=False)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)

list(self.vgg_features.modules())的结果为

0 Sequential(
  (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (1): ReLU(inplace=True)
  (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (3): ReLU(inplace=True)
  (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (6): ReLU(inplace=True)
  (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (8): ReLU(inplace=True)
  (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (11): ReLU(inplace=True)
  (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (13): ReLU(inplace=True)
  (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (15): ReLU(inplace=True)
  (16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (17): ReLU(inplace=True)
  (18): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (19): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (20): ReLU(inplace=True)
  (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (22): ReLU(inplace=True)
  (23): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (24): ReLU(inplace=True)
  (25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (26): ReLU(inplace=True)
  (27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (29): ReLU(inplace=True)
  (30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (31): ReLU(inplace=True)
  (32): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (33): ReLU(inplace=True)
  (34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (35): ReLU(inplace=True)
  (36): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
1 Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
2 ReLU(inplace=True)
3 Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
4 ReLU(inplace=True)
5 MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
6 Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
7 ReLU(inplace=True)
8 Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
9 ReLU(inplace=True)
10 MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
11 Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
12 ReLU(inplace=True)
13 Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
14 ReLU(inplace=True)
15 Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
16 ReLU(inplace=True)
17 Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
18 ReLU(inplace=True)
19 MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
20 Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
21 ReLU(inplace=True)
22 Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
23 ReLU(inplace=True)
24 Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
25 ReLU(inplace=True)
26 Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
27 ReLU(inplace=True)
28 MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
29 Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
30 ReLU(inplace=True)
31 Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
32 ReLU(inplace=True)
33 Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
34 ReLU(inplace=True)
35 Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
36 ReLU(inplace=True)
37 MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)

model.modules()和model.children()均为迭代器，model.modules()会遍历model中所有的子层，而model.children()仅会遍历当前层

# model.modules()类似于 [[1, 2], 3],其遍历结果为：
[[1, 2], 3], [1, 2], 1, 2, 3
 
# model.children()类似于 [[1, 2], 3],其遍历结果为：
[1, 2], 3

def addlist2(model):
    module_list = list()
    for layer in model.children():  # .named_modules():
        # print(len(layer))
        if (type(layer) is nn.Sequential):
            for sublayer in layer:
                module_list.append(sublayer)
        else:
            module_list.append(layer)
            # if sublayer is
            # print(type(sublayer), sublayer)
            # print(type(layer),layer)
    #
    '''for module_idx, module in enumerate(module_list):
        print(module_idx, module)'''
    return module_list

class Resnet18_Extractor_assigned2(nn.Module):
    def __init__(self, output_layer_list=[2, 7, 16, 25]):  #
        super(Resnet18_Extractor_assigned2, self).__init__()
        fth = r'G:pytorch_classification-masterdatasetweightsresnet18epoch_560.pth'
        checkp = torch.load(fth)  # , map_location='cuda:0')
        #print(checkp.keys())  # checkp.items()
        model = checkp['model']  # 提取网络结构
        model.load_state_dict(checkp['model_state_dict'])  # 加载网络权重参数
        self.classer=model
        self.module_list =addlist2(self.classer)# list(self.classer.children())#[1:]
        #print(self.classer)
        print('###########################')
        for module_idx, module in enumerate(self.module_list):
            print(module_idx, module)
        #self.classer
        self.mean = nn.Parameter(torch.Tensor([0.485, 0.456, 0.406]).view(1, 3, 1, 1), requires_grad=False).cuda()
        self.std = nn.Parameter(torch.Tensor([0.229, 0.224, 0.225]).view(1, 3, 1, 1), requires_grad=False).cuda()

    def forward(self, x):
        # print('shpe',x.shape,self.mean.repeat(x.size(0),1,x.size(2),x.size(3)).shape)
        #x = x - self.mean.repeat(x.size(0), 1, x.size(2), x.size(3))
        #x = x / self.std.repeat(x.size(0), 1, x.size(2), x.size(3))
        x = x - self.mean.repeat(x.size(0), 1, x.size(2), x.size(3))
        x = x / self.std.repeat(x.size(0), 1, x.size(2), x.size(3))
        output_list = []
        for module_idx, module in enumerate(self.module_list):

            x = module(x)
            if isinstance(module, nn.AdaptiveAvgPool2d):
                x = torch.flatten(x, 1)
            print('resnet',module_idx,x.shape)#,module) #0-36
            '''if module_idx in self.output_layer_list:  # module_idx in output_layer_list:#self.output_layer_list:
                output_list.append(x)'''
        return output_list

input_tensor = torch.ones([1, 3, 320, 320], dtype=torch.float32)
input_tensor=input_tensor.cuda()
vgg19_extractor_assigned = Resnet18_Extractor_assigned2(output_layer_list=[3, 8, 17, 26])
out = vgg19_extractor_assigned(input_tensor)

其中resnet18的网络结构为

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): BasicBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=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)
    )
    (1): BasicBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=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)
    )
  )
  (layer2): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=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)
      (downsample): Sequential(
        (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=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)
    )
  )
  (layer3): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=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)
      (downsample): Sequential(
        (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=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)
    )
  )
  (layer4): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=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)
      (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): BasicBlock(
      (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=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)
    )
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
  (fc): Linear(in_features=512, out_features=2, bias=True)
)

代码输出为

###########################
0 Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
1 BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
2 ReLU(inplace=True)
3 MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
4 BasicBlock(
  (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=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)
)
5 BasicBlock(
  (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=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)
)
6 BasicBlock(
  (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
  (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=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)
  (downsample): Sequential(
    (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
    (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  )
)
7 BasicBlock(
  (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=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)
)
8 BasicBlock(
  (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
  (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=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)
  (downsample): Sequential(
    (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
    (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  )
)
9 BasicBlock(
  (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=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)
)
10 BasicBlock(
  (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
  (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=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)
  (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)
  )
)
11 BasicBlock(
  (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=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)
)
12 AdaptiveAvgPool2d(output_size=(1, 1))
13 Linear(in_features=512, out_features=2, bias=True)
resnet 0 torch.Size([1, 64, 160, 160])
resnet 1 torch.Size([1, 64, 160, 160])
resnet 2 torch.Size([1, 64, 160, 160])
resnet 3 torch.Size([1, 64, 80, 80])
resnet 4 torch.Size([1, 64, 80, 80])
resnet 5 torch.Size([1, 64, 80, 80])
resnet 6 torch.Size([1, 128, 40, 40])
resnet 7 torch.Size([1, 128, 40, 40])
resnet 8 torch.Size([1, 256, 20, 20])
resnet 9 torch.Size([1, 256, 20, 20])
resnet 10 torch.Size([1, 512, 10, 10])
resnet 11 torch.Size([1, 512, 10, 10])
resnet 12 torch.Size([1, 512])
resnet 13 torch.Size([1, 2])