PyTorch 搭建卷積神經網絡

關於卷積神經網絡的理論基礎不再詳細說明，具體可見 卷積神經網絡CNN。

1 卷積層

import torch

in_channels, out_channels = 5, 10
width, heigh = 100, 100
kernal_size = 3
batch_size = 1  # PyTorch中所有輸入數據都是小批量處理

input = torch.randn(batch_size,
                    in_channels,
                    width,
                    heigh)

conv_layer = torch.nn.Conv2d(in_channels,
                             out_channels,
                             kernel_size=kernal_size)
output = conv_layer(input)

print(input.shape)
print(output.shape)
print(conv_layer.weight.shape)

　　輸出：

torch.Size([1, 5, 100, 100])
torch.Size([1, 10, 98, 98])
torch.Size([10, 5, 3, 3])

　　這里的輸入為 5 通道的 100*100 大小圖像，該卷積層包括 10 個卷積核，每個卷積核為 5 通道的 3*3 大小，因此輸出為 10 通道的 98*98 大小圖像。

　　輸入的通道數就是卷積核的通道數，輸出的通道數就是卷積核的個數。

　　如果不想改變圖像大小，可以使用 padding 填充圖像：

import torch

input = [3, 4, 6, 5, 7,
         2, 4, 6, 8, 2,
         1, 6, 7, 8, 4,
         9, 7, 4, 6, 2,
         3, 7, 5, 4, 1]
input = torch.Tensor(input).view(1, 1, 5, 5)

conv_layer = torch.nn.Conv2d(1, 1, kernel_size=3, padding=1, bias=False)

kernal = torch.Tensor([1, 2, 3, 4, 5, 6, 7, 8, 9]).view(1, 1, 3, 3)
conv_layer.weight.data = kernal

output = conv_layer(input)
print(output)

　　輸出：

tensor([[[[ 91., 168., 224., 215., 127.],
          [114., 211., 295., 262., 149.],
          [192., 259., 282., 214., 122.],
          [194., 251., 253., 169.,  86.],
          [ 96., 112., 110.,  68.,  31.]]]], grad_fn=<ThnnConv2DBackward>)

　　還可以設置歩長 stride ：

conv_layer = torch.nn.Conv2d(1, 1, kernel_size=3, stride=2, bias=False)

2 池化層

import torch

input = [3, 4, 6, 5,
         2, 4, 6, 8,
         1, 6, 7, 8,
         9, 7, 4, 6]
input = torch.Tensor(input).view(1, 1, 4, 4)

maxpooling_layer = torch.nn.MaxPool2d(kernel_size=2)

output = maxpooling_layer(input)
print(output)

　　輸出：

tensor([[[[4., 8.],
          [9., 8.]]]])

　　一般不會改變通道數。

2 卷積神經網絡

　　我們構建一個如下圖所示的網絡來訓練手寫數字集 MNIST

 

 　　完整代碼如下：

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

train_dataset = datasets.MNIST(root='../dataset/mnist',
                               train=True,
                               transform=transform,
                               download=True)
test_dataset = datasets.MNIST(root='../dataset/mnist',
                              train=False,
                              transform=transform,
                              download=True)
train_loader = DataLoader(dataset=train_dataset,
                          batch_size=batch_size,
                          shuffle=True)
test_loader = DataLoader(dataset=test_dataset,
                         batch_size=batch_size,
                         shuffle=False)

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(320, 10)

    def forward(self, x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size, -1)  # flatten
        x = self.fc(x)
        return x

model = Net()
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch+1, batch_idx+1, running_loss/300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():  # 測試不需要計算梯度
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
        print('Accuracy on test set: %d %%' % (100 * correct / total))

if __name__ == '__main__':
    for epoch in range(100):
        train(epoch)
        test()

　　如何使用 GPU 訓練神經網絡：

　　1. 將模型遷移到 GPU

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

　　2. 將數據遷移到 GPU

inputs, target = inputs.to(device), target.to(device)

　　完整代碼如下：

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))
])

train_dataset = datasets.MNIST(root='../dataset/mnist',
                               train=True,
                               transform=transform,
                               download=True)
test_dataset = datasets.MNIST(root='../dataset/mnist',
                              train=False,
                              transform=transform,
                              download=True)
train_loader = DataLoader(dataset=train_dataset,
                          batch_size=batch_size,
                          shuffle=True)
test_loader = DataLoader(dataset=test_dataset,
                         batch_size=batch_size,
                         shuffle=False)

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(320, 10)

    def forward(self, x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size, -1)  # flatten
        x = self.fc(x)
        return x

model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch+1, batch_idx+1, running_loss/300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():  # 測試不需要計算梯度
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
        print('Accuracy on test set: %d %%' % (100 * correct / total))

if __name__ == '__main__':
    for epoch in range(100):
        train(epoch)
        test()