【Pytorch】10行代码搞定可视化网络模型中间输出

环境:

python3.6.8
torch == 1.3.1
torchvision == 0.4.1

---

import torch
import torch.optim as optim
import torch.nn.functional as F
import torchvision
import torchvision.datasets as datasets
import torchvision.models as models
import torchvision.transforms as transforms

model = models.alexnet(pretrained=False)
print(model)
'''
AlexNet(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
    (1): ReLU(inplace=True)
    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (4): ReLU(inplace=True)
    (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU(inplace=True)
    (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (9): ReLU(inplace=True)
    (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace=True)
    (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(6, 6))
  (classifier): Sequential(
    (0): Dropout(p=0.5, inplace=False)
    (1): Linear(in_features=9216, out_features=4096, bias=True)
    (2): ReLU(inplace=True)
    (3): Dropout(p=0.5, inplace=False)
    (4): Linear(in_features=4096, out_features=4096, bias=True)
    (5): ReLU(inplace=True)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)
'''
print(model.features)
'''
Sequential(
  (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
  (1): ReLU(inplace=True)
  (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
  (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
  (4): ReLU(inplace=True)
  (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
  (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (7): ReLU(inplace=True)
  (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (9): ReLU(inplace=True)
  (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (11): ReLU(inplace=True)
  (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
)
'''
from PIL import Image
import numpy as np
img = Image.open('cat.jpg')
out = model.features(transforms.ToTensor()(img).unsqueeze(0))
print(out.shape)
'''
torch.Size([1, 256, 14, 14])
'''
out = out.squeeze()
print(out.shape)
'''
torch.Size([256, 14, 14])
'''
import matplotlib.pyplot as plt
plt.figure(figsize=(2,2),dpi=100)
plt.imshow(img)
plt.show()
plt.figure(figsize=(12,12),dpi=100)
for index,item in enumerate(out):
    plt.subplot(8,8,index+1)
    plt.imshow(transforms.ToPILImage()(item),cmap='gray')
    if index==63:
        break
plt.show()

最简代码:

import torch
import torch.optim as optim
import torch.nn.functional as F
import torchvision
import torchvision.datasets as datasets
import torchvision.models as models
import torchvision.transforms as transforms
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
model = models.alexnet(pretrained=False)
img = Image.open('cat.jpg')
out = model.features(transforms.ToTensor()(img).unsqueeze(0)).squeeze()
plt.figure(figsize=(2,2),dpi=100)
plt.imshow(img)
plt.show()
plt.figure(figsize=(12,12),dpi=100)
for index,item in enumerate(out):
    plt.subplot(8,8,index+1)
    plt.imshow(transforms.ToPILImage()(item),cmap='gray')
    if index==63:
        break
plt.show()