可视化与生态

将结合torchvision预定义的ResNet模型来探索PyTorch的可视化方案。

可视化网络结构

这里我们使用torchinfo开源工具包，介绍网络结构可视化方案

可视化网络结构需要进行一次前向传播以获得特定属性信息

import os
import numpy as np
import matplotlib.pyplot as plt
import torch
import torchvision.models as models
from torchinfo import summary
os.environ['CUDA_VISIBLE_DEVICES'] = '0'

resnet18 = models.resnet18()
resnet18

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=1000, bias=True)
)

## 可视化网络结构的重点在于看“Output Shape” 和 “Param”
summary(resnet18, (1, 3, 224, 224))

==========================================================================================
Layer (type:depth-idx)                   Output Shape              Param #
==========================================================================================
ResNet                                   --                        --
├─Conv2d: 1-1                            [1, 64, 112, 112]         9,408
├─BatchNorm2d: 1-2                       [1, 64, 112, 112]         128
├─ReLU: 1-3                              [1, 64, 112, 112]         --
├─MaxPool2d: 1-4                         [1, 64, 56, 56]           --
├─Sequential: 1-5                        [1, 64, 56, 56]           --
│    └─BasicBlock: 2-1                   [1, 64, 56, 56]           --
│    │    └─Conv2d: 3-1                  [1, 64, 56, 56]           36,864
│    │    └─BatchNorm2d: 3-2             [1, 64, 56, 56]           128
│    │    └─ReLU: 3-3                    [1, 64, 56, 56]           --
│    │    └─Conv2d: 3-4                  [1, 64, 56, 56]           36,864
│    │    └─BatchNorm2d: 3-5             [1, 64, 56, 56]           128
│    │    └─ReLU: 3-6                    [1, 64, 56, 56]           --
│    └─BasicBlock: 2-2                   [1, 64, 56, 56]           --
│    │    └─Conv2d: 3-7                  [1, 64, 56, 56]           36,864
│    │    └─BatchNorm2d: 3-8             [1, 64, 56, 56]           128
│    │    └─ReLU: 3-9                    [1, 64, 56, 56]           --
│    │    └─Conv2d: 3-10                 [1, 64, 56, 56]           36,864
│    │    └─BatchNorm2d: 3-11            [1, 64, 56, 56]           128
│    │    └─ReLU: 3-12                   [1, 64, 56, 56]           --
├─Sequential: 1-6                        [1, 128, 28, 28]          --
│    └─BasicBlock: 2-3                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-13                 [1, 128, 28, 28]          73,728
│    │    └─BatchNorm2d: 3-14            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-15                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-16                 [1, 128, 28, 28]          147,456
│    │    └─BatchNorm2d: 3-17            [1, 128, 28, 28]          256
│    │    └─Sequential: 3-18             [1, 128, 28, 28]          8,448
│    │    └─ReLU: 3-19                   [1, 128, 28, 28]          --
│    └─BasicBlock: 2-4                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-20                 [1, 128, 28, 28]          147,456
│    │    └─BatchNorm2d: 3-21            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-22                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-23                 [1, 128, 28, 28]          147,456
│    │    └─BatchNorm2d: 3-24            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-25                   [1, 128, 28, 28]          --
├─Sequential: 1-7                        [1, 256, 14, 14]          --
│    └─BasicBlock: 2-5                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-26                 [1, 256, 14, 14]          294,912
│    │    └─BatchNorm2d: 3-27            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-28                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-29                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-30            [1, 256, 14, 14]          512
│    │    └─Sequential: 3-31             [1, 256, 14, 14]          33,280
│    │    └─ReLU: 3-32                   [1, 256, 14, 14]          --
│    └─BasicBlock: 2-6                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-33                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-34            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-35                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-36                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-37            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-38                   [1, 256, 14, 14]          --
├─Sequential: 1-8                        [1, 512, 7, 7]            --
│    └─BasicBlock: 2-7                   [1, 512, 7, 7]            --
│    │    └─Conv2d: 3-39                 [1, 512, 7, 7]            1,179,648
│    │    └─BatchNorm2d: 3-40            [1, 512, 7, 7]            1,024
│    │    └─ReLU: 3-41                   [1, 512, 7, 7]            --
│    │    └─Conv2d: 3-42                 [1, 512, 7, 7]            2,359,296
│    │    └─BatchNorm2d: 3-43            [1, 512, 7, 7]            1,024
│    │    └─Sequential: 3-44             [1, 512, 7, 7]            132,096
│    │    └─ReLU: 3-45                   [1, 512, 7, 7]            --
│    └─BasicBlock: 2-8                   [1, 512, 7, 7]            --
│    │    └─Conv2d: 3-46                 [1, 512, 7, 7]            2,359,296
│    │    └─BatchNorm2d: 3-47            [1, 512, 7, 7]            1,024
│    │    └─ReLU: 3-48                   [1, 512, 7, 7]            --
│    │    └─Conv2d: 3-49                 [1, 512, 7, 7]            2,359,296
│    │    └─BatchNorm2d: 3-50            [1, 512, 7, 7]            1,024
│    │    └─ReLU: 3-51                   [1, 512, 7, 7]            --
├─AdaptiveAvgPool2d: 1-9                 [1, 512, 1, 1]            --
├─Linear: 1-10                           [1, 1000]                 513,000
==========================================================================================
Total params: 11,689,512
Trainable params: 11,689,512
Non-trainable params: 0
Total mult-adds (G): 1.81
==========================================================================================
Input size (MB): 0.60
Forward/backward pass size (MB): 39.75
Params size (MB): 46.76
Estimated Total Size (MB): 87.11
==========================================================================================

可视化CNN卷积核

## 首先看下网络中哪些是卷积层，因为只有卷积层才会有卷积核的概念
print(dict(resnet18.named_children()))

{'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=1000, bias=True)}

dict(resnet18.named_children())["conv1"]

Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)

## 我们选择第一个卷积层来进行可视化，注意卷积核的参数并没有经过训练仍是初始化的状态
## 上面显示kernel_size是（7,7），对应于下面图像的大小
conv1 = dict(resnet18.named_children())["conv1"]
kernel_set = conv1.weight.cpu().detach()
num = len(conv1.weight.cpu().detach())
print(num, kernel_set.shape)
for i in range(0, num):
    i_kernel = kernel_set[i]
    plt.figure(figsize=(20, 17))
    if (len(i_kernel)) > 1:
        for idx, filer in enumerate(i_kernel):
            plt.subplot(9, 9, idx+1)
            plt.axis('off')
            plt.imshow(filer[ :, : ].detach(), cmap='bwr')

64 torch.Size([64, 3, 7, 7])


D:\ProgramData\Anaconda3\envs\pytorch\lib\site-packages\ipykernel_launcher.py:9: RuntimeWarning: More than 20 figures have been opened. Figures created through the pyplot interface (`matplotlib.pyplot.figure`) are retained until explicitly closed and may consume too much memory. (To control this warning, see the rcParam `figure.max_open_warning`).
  if __name__ == '__main__':

CNN特征图可视化

这里用到了PyTorch中的hook接口，相当于数据进行前向传播过程中的特征图会被hook捕捉，前向传播之后可以另行查看

class Hook(object):
    def __init__(self):
        self.module_name = []
        self.features_in_hook = []
        self.features_out_hook = []
        
    def __call__(self, module, fea_in, fea_out):
        print("hooker working", self)
        self.module_name.append(module.__class__)
        self.features_in_hook.append(fea_in)
        self.features_out_hook.append(fea_out)
        return None

inputs = torch.rand(1,3,224,224).cuda()

hh = Hook()
dict(resnet18.named_children())["conv1"].register_forward_hook(hh)

resnet18.eval()
_ = resnet18(inputs)
print(hh.module_name)
print((hh.features_in_hook[0][0].shape))
print((hh.features_out_hook[0].shape))

out1 = hh.features_out_hook[0]

total_ft = out1.shape[1]
first_item = out1[0].cpu().clone()

plt.figure(figsize=(20, 17))

for ftidx in range(total_ft):
    if ftidx > 99:
        break
    ft = first_item(ftidx)
    plt.subplot(10, 10, ftidx+1)
    
    plt.axis('off')
    plt.imshow(ft[:,:].detach())

hooker working <__main__.Hook object at 0x000001CF9A22BEC8>



---------------------------------------------------------------------------

AttributeError                            Traceback (most recent call last)

~\AppData\Local\Temp\ipykernel_15008\3746997551.py in 
      5 
      6 resnet18.eval()
----> 7 _ = resnet18(inputs)
      8 print(hh.module_name)
      9 print((hh.features_in_hook[0][0].shape))


D:\ProgramData\Anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
    530             result = self._slow_forward(*input, **kwargs)
    531         else:
--> 532             result = self.forward(*input, **kwargs)
    533         for hook in self._forward_hooks.values():
    534             hook_result = hook(self, input, result)


D:\ProgramData\Anaconda3\envs\pytorch\lib\site-packages\torchvision\models\resnet.py in forward(self, x)
    214 
    215     def forward(self, x):
--> 216         return self._forward_impl(x)
    217 
    218 


D:\ProgramData\Anaconda3\envs\pytorch\lib\site-packages\torchvision\models\resnet.py in _forward_impl(self, x)
    197     def _forward_impl(self, x):
    198         # See note [TorchScript super()]
--> 199         x = self.conv1(x)
    200         x = self.bn1(x)
    201         x = self.relu(x)


D:\ProgramData\Anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
    532             result = self.forward(*input, **kwargs)
    533         for hook in self._forward_hooks.values():
--> 534             hook_result = hook(self, input, result)
    535             if hook_result is not None:
    536                 result = hook_result


~\AppData\Local\Temp\ipykernel_15008\773438108.py in __call__(self, module, fea_in, fea_out)
      8         print("hooker working", self)
      9         self.module_name.append(module.__class__)
---> 10         self.features_in_hook.append(fea_in)
     11         self.features_out_hook.append(fea_out)
     12         return None


AttributeError: 'Hook' object has no attribute 'features_in_hook'