PyTorchを利用してVGG 16教程を実現します。

余計なことを言わないで、コードを見てください。

import torch
import torch.nn as nn
import torch.nn.functional as F
class VGG16(nn.Module):
 
 def __init__(self):
  super(VGG16, self).__init__()
  
  # 3 * 224 * 224
  self.conv1_1 = nn.Conv2d(3, 64, 3) # 64 * 222 * 222
  self.conv1_2 = nn.Conv2d(64, 64, 3, padding=(1, 1)) # 64 * 222* 222
  self.maxpool1 = nn.MaxPool2d((2, 2), padding=(1, 1)) # pooling 64 * 112 * 112
  
  self.conv2_1 = nn.Conv2d(64, 128, 3) # 128 * 110 * 110
  self.conv2_2 = nn.Conv2d(128, 128, 3, padding=(1, 1)) # 128 * 110 * 110
  self.maxpool2 = nn.MaxPool2d((2, 2), padding=(1, 1)) # pooling 128 * 56 * 56
  
  self.conv3_1 = nn.Conv2d(128, 256, 3) # 256 * 54 * 54
  self.conv3_2 = nn.Conv2d(256, 256, 3, padding=(1, 1)) # 256 * 54 * 54
  self.conv3_3 = nn.Conv2d(256, 256, 3, padding=(1, 1)) # 256 * 54 * 54
  self.maxpool3 = nn.MaxPool2d((2, 2), padding=(1, 1)) # pooling 256 * 28 * 28
  
  self.conv4_1 = nn.Conv2d(256, 512, 3) # 512 * 26 * 26
  self.conv4_2 = nn.Conv2d(512, 512, 3, padding=(1, 1)) # 512 * 26 * 26
  self.conv4_3 = nn.Conv2d(512, 512, 3, padding=(1, 1)) # 512 * 26 * 26
  self.maxpool4 = nn.MaxPool2d((2, 2), padding=(1, 1)) # pooling 512 * 14 * 14
  
  self.conv5_1 = nn.Conv2d(512, 512, 3) # 512 * 12 * 12
  self.conv5_2 = nn.Conv2d(512, 512, 3, padding=(1, 1)) # 512 * 12 * 12
  self.conv5_3 = nn.Conv2d(512, 512, 3, padding=(1, 1)) # 512 * 12 * 12
  self.maxpool5 = nn.MaxPool2d((2, 2), padding=(1, 1)) # pooling 512 * 7 * 7
  # view
  
  self.fc1 = nn.Linear(512 * 7 * 7, 4096)
  self.fc2 = nn.Linear(4096, 4096)
  self.fc3 = nn.Linear(4096, 1000)
  # softmax 1 * 1 * 1000
  
 def forward(self, x):
  
  # x.size(0)  batch_size
  in_size = x.size(0)
  
  out = self.conv1_1(x) # 222
  out = F.relu(out)
  out = self.conv1_2(out) # 222
  out = F.relu(out)
  out = self.maxpool1(out) # 112
  
  out = self.conv2_1(out) # 110
  out = F.relu(out)
  out = self.conv2_2(out) # 110
  out = F.relu(out)
  out = self.maxpool2(out) # 56
  
  out = self.conv3_1(out) # 54
  out = F.relu(out)
  out = self.conv3_2(out) # 54
  out = F.relu(out)
  out = self.conv3_3(out) # 54
  out = F.relu(out)
  out = self.maxpool3(out) # 28
  
  out = self.conv4_1(out) # 26
  out = F.relu(out)
  out = self.conv4_2(out) # 26
  out = F.relu(out)
  out = self.conv4_3(out) # 26
  out = F.relu(out)
  out = self.maxpool4(out) # 14
  
  out = self.conv5_1(out) # 12
  out = F.relu(out)
  out = self.conv5_2(out) # 12
  out = F.relu(out)
  out = self.conv5_3(out) # 12
  out = F.relu(out)
  out = self.maxpool5(out) # 7
  
  #   
  out = out.view(in_size, -1)
  
  out = self.fc1(out)
  out = F.relu(out)
  out = self.fc2(out)
  out = F.relu(out)
  out = self.fc3(out)
  
  out = F.log_softmax(out, dim=1)
  return out

追加知識：PytouchはVGG（GPU版）を実現します。
コードを見ましょう

import torch
from torch import nn
from torch import optim
from PIL import Image
import numpy as np

print(torch.cuda.is_available())
device = torch.device('cuda:0')
path="/content/drive/My Drive/Colab Notebooks/data/dog_vs_cat/"

train_X=np.empty((2000,224,224,3),dtype="float32")
train_Y=np.empty((2000,),dtype="int")
train_XX=np.empty((2000,3,224,224),dtype="float32")

for i in range(1000):
 file_path=path+"cat."+str(i)+".jpg"
 image=Image.open(file_path)
 resized_image = image.resize((224, 224), Image.ANTIALIAS)
 img=np.array(resized_image)
 train_X[i,:,:,:]=img
 train_Y[i]=0

for i in range(1000):
 file_path=path+"dog."+str(i)+".jpg"
 image = Image.open(file_path)
 resized_image = image.resize((224, 224), Image.ANTIALIAS)
 img = np.array(resized_image)
 train_X[i+1000, :, :, :] = img
 train_Y[i+1000] = 1

train_X /= 255

index = np.arange(2000)
np.random.shuffle(index)

train_X = train_X[index, :, :, :]
train_Y = train_Y[index]

for i in range(3):
 train_XX[:,i,:,:]=train_X[:,:,:,i]
#     

class Net(nn.Module):

 def __init__(self):
  super(Net, self).__init__()
  self.conv1 = nn.Sequential(
   nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.BatchNorm2d(num_features=64, eps=1e-05, momentum=0.1, affine=True),
   nn.MaxPool2d(kernel_size=2,stride=2)
  )
  self.conv2 = nn.Sequential(
   nn.Conv2d(in_channels=64,out_channels=128,kernel_size=3,stride=1,padding=1),
   nn.ReLU(),
   nn.Conv2d(in_channels=128, out_channels=128, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.BatchNorm2d(128,eps=1e-5,momentum=0.1,affine=True),
   nn.MaxPool2d(kernel_size=2,stride=2)
  )
  self.conv3 = nn.Sequential(
   nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.BatchNorm2d(256,eps=1e-5, momentum=0.1, affine=True),
   nn.MaxPool2d(kernel_size=2, stride=2)
  )
  self.conv4 = nn.Sequential(
   nn.Conv2d(in_channels=256, out_channels=512, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.BatchNorm2d(512, eps=1e-5, momentum=0.1, affine=True),
   nn.MaxPool2d(kernel_size=2, stride=2)
  )
  self.conv5 = nn.Sequential(
   nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1),
   nn.ReLU(),
   nn.BatchNorm2d(512, eps=1e-5, momentum=0.1, affine=True),
   nn.MaxPool2d(kernel_size=2, stride=2)
  )
  self.dense1 = nn.Sequential(
   nn.Linear(7*7*512,4096),
   nn.ReLU(),
   nn.Linear(4096,4096),
   nn.ReLU(),
   nn.Linear(4096,2)
  )

 def forward(self, x):
  x=self.conv1(x)
  x=self.conv2(x)
  x=self.conv3(x)
  x=self.conv4(x)
  x=self.conv5(x)
  x=x.view(-1,7*7*512)
  x=self.dense1(x)
  return x

batch_size=16
net = Net().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.0005)

train_loss = []
for epoch in range(10):

 for i in range(2000//batch_size):
  x=train_XX[i*batch_size:i*batch_size+batch_size]
  y=train_Y[i*batch_size:i*batch_size+batch_size]

  x = torch.from_numpy(x)  #(batch_size,input_feature_shape)
  y = torch.from_numpy(y)  #(batch_size,label_onehot_shape)
  x = x.cuda()
  y = y.long().cuda()

  out = net(x)

  loss = criterion(out, y)   #        
  optimizer.zero_grad()    #              
  loss.backward()     #       ,        
  optimizer.step()     #           net   parameters  
  train_loss.append(loss.item())

  print(epoch, i*batch_size, np.mean(train_loss))
  train_loss=[]

total_correct = 0
for i in range(2000):
 x = train_XX[i].reshape(1,3,224,224)
 y = train_Y[i]
 x = torch.from_numpy(x)

 x = x.cuda()
 out = net(x).cpu()
 out = out.detach().numpy()
 pred=np.argmax(out)
 if pred==y:
  total_correct += 1
 print(total_correct)

acc = total_correct / 2000.0
print('test acc:', acc)

torch.cuda.empty_cache()

上のコードの中のbatch_をsizeを32に変えて、トレーニング回数を100ラウンドに変えて、次のような正確さを得ます。

フィットしすぎました
以上のPyTorchを利用してVGG 16教程を実現しました。つまり、小編纂は皆さんに全部の内容を共有しています。参考にしてもらいたいです。どうぞよろしくお願いします。