neural_network.py

"""
@author:  liaoxingyu
@contact: sherlockliao01@gmail.com
"""

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets, transforms

batch_size = 64
learning_rate = 1e-2
num_epochs = 50
use_gpu = torch.cuda.is_available()

# 下载训练集 MNIST 手写数字训练集
train_dataset = datasets.FashionMNIST(
    root='../datasets', train=True, transform=transforms.ToTensor(), download=True)

test_dataset = datasets.FashionMNIST(
    root='../datasets', train=False, transform=transforms.ToTensor())

train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)


# 定义简单的前馈神经网络
class neuralNetwork(nn.Module):
    def __init__(self, in_dim, n_hidden_1, n_hidden_2, out_dim):
        super(neuralNetwork, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Linear(in_dim, n_hidden_1),
            nn.ReLU(True))
        self.layer2 = nn.Sequential(
            nn.Linear(n_hidden_1, n_hidden_2),
            nn.ReLU(True))
        self.layer3 = nn.Sequential(
            nn.Linear(n_hidden_2, out_dim),
            nn.ReLU(True))

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return x

model = neuralNetwork(28 * 28, 300, 100, 10)
if use_gpu:
    model = model.cuda()

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

for epoch in range(num_epochs):
    print('*' * 10)
    print(f'epoch {epoch+1}')
    running_loss = 0.0
    running_acc = 0.0
    for i, data in enumerate(train_loader, 1):
        img, label = data
        img = img.view(img.size(0), -1)
        if use_gpu:
            img = img.cuda()
            label = label.cuda()
        # 向前传播
        out = model(img)
        loss = criterion(out, label)
        running_loss += loss.item()
        _, pred = torch.max(out, 1)
        running_acc += (pred == label).float().mean()
        # 向后传播
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if i % 300 == 0:
            print(f'[{epoch+1}/{num_epochs}] Loss: {running_loss/i:.6f}, Acc: {running_acc/i:.6f}')
    print(f'Finish {epoch+1} epoch, Loss: {running_loss/i:.6f}, Acc: {running_acc/i:.6f}')
    model.eval()
    eval_loss = 0.
    eval_acc = 0.
    for data in test_loader:
        img, label = data
        img = img.view(img.size(0), -1)
        if use_gpu:
            img = img.cuda()
            label = label.cuda()
        with torch.no_grad():
            out = model(img)
            loss = criterion(out, label)
        eval_loss += loss.item()
        _, pred = torch.max(out, 1)
        eval_acc += (pred == label).float().mean()
    print(f'Test Loss: {eval_loss/len(test_loader):.6f}, Acc: {eval_acc/len(test_loader):.6f}\n')

# 保存模型
torch.save(model.state_dict(), './neural_network.pth')