PyTorch——LeNet实现（附完整代码）

参考链接

1. https://tangshusen.me/Dive-into-DL-PyTorch/#/chapter05_CNN/5.5_lenet

LeNet

LeNet分为卷积层块和全连接层块两个部分。

卷积层块里的基本单位是卷积层后接最大池化层：卷积层用来识别图像里的空间模式，如线条和物体局部，之后的最大池化层则用来降低卷积层对位置的敏感性。在卷积层块中，每个卷积层都使用5×5的窗口，并在输出上使用sigmoid激活函数。第一个卷积层输出通道数为6，第二个卷积层输出通道数则增加到16。这是因为第二个卷积层比第一个卷积层的输入的高和宽要小，所以增加输出通道使两个卷积层的参数尺寸类似。卷积层块的两个最大池化层的窗口形状均为2×2，且步幅为2。

加载数据

使用“Fashion-MNIST”数据集。

mnist_train = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=True, download=True, transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=False, download=True, transform=transforms.ToTensor())

def load_data_fashion_mnist(mnist_train, mnist_test, batch_size):
    if sys.platform.startswith('win'):
        num_workers = 0
    else:
        num_workers = 4
    train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)
    test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)
    return train_iter, test_iter

batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(mnist_train, mnist_test, batch_size)

构建模型

class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 6, 5), # in_channels, out_channels, kernel_size
            nn.Sigmoid(),
            nn.MaxPool2d(2, 2), # kernel_size, stride
            nn.Conv2d(6, 16, 5),
            nn.Sigmoid(),
            nn.MaxPool2d(2, 2)
        )
        self.fc = nn.Sequential(
            nn.Linear(16*4*4, 120),
            nn.Sigmoid(),
            nn.Linear(120, 84),
            nn.Sigmoid(),
            nn.Linear(84, 10)
        )

    def forward(self, img):
        feature = self.conv(img)
        output = self.fc(feature.view(img.shape[0], -1))
        return output

损失函数

损失函数使用交叉熵损失。

loss = torch.nn.CrossEntropyLoss()

优化方法

优化方法使用Adam算法。

optimizer = torch.optim.Adam(net.parameters(), lr=lr)

完整代码

import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
import torchvision
import torchvision.transforms as transforms
import time

mnist_train = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=True, download=True, transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=False, download=True, transform=transforms.ToTensor())

def load_data_fashion_mnist(mnist_train, mnist_test, batch_size):
    if sys.platform.startswith('win'):
        num_workers = 0
    else:
        num_workers = 4
    train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)
    test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)
    return train_iter, test_iter

batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(mnist_train, mnist_test, batch_size)

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 6, 5), # in_channels, out_channels, kernel_size
            nn.Sigmoid(),
            nn.MaxPool2d(2, 2), # kernel_size, stride
            nn.Conv2d(6, 16, 5),
            nn.Sigmoid(),
            nn.MaxPool2d(2, 2)
        )
        self.fc = nn.Sequential(
            nn.Linear(16*4*4, 120),
            nn.Sigmoid(),
            nn.Linear(120, 84),
            nn.Sigmoid(),
            nn.Linear(84, 10)
        )

    def forward(self, img):
        feature = self.conv(img)
        output = self.fc(feature.view(img.shape[0], -1))
        return output

net = LeNet()

def evaluate_accuracy(data_iter, net, device=None):
    if device is None and isinstance(net, torch.nn.Module):
        # 如果没指定device就使用net的device
        device = list(net.parameters())[0].device
    acc_sum, n = 0.0, 0
    with torch.no_grad():
        for X, y in data_iter:
            net.eval() # 评估模式, 这会关闭dropout
            acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()
            net.train() # 改回训练模式
            n += y.shape[0]
    return acc_sum / n


def train(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs):
    net = net.to(device)
    print("training on ", device)
    loss = torch.nn.CrossEntropyLoss()
    for epoch in range(num_epochs):
        train_l_sum, train_acc_sum, n, batch_count, start = 0.0, 0.0, 0, 0, time.time()
        for X, y in train_iter:
            X = X.to(device)
            y = y.to(device)
            y_hat = net(X)
            l = loss(y_hat, y)
            optimizer.zero_grad()
            l.backward()
            optimizer.step()
            train_l_sum += l.cpu().item()
            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().cpu().item()
            n += y.shape[0]
            batch_count += 1
        test_acc = evaluate_accuracy(test_iter, net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f, time %.1f sec'
              % (epoch + 1, train_l_sum / batch_count, train_acc_sum / n, test_acc, time.time() - start))

lr, num_epochs = 0.001, 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
train(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs)