【pytorch-tutorial自学笔记】01-basic-logistic_regression

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Hyper-parameters
input_size = 28 * 28  # 784
num_classes = 10
num_epochs = 5
batch_size = 100
learning_rate = 0.001

# MNIST dataset (images and labels)
train_dataset = torchvision.datasets.MNIST(root='../../data',
                                           train=True,
                                           transform=transforms.ToTensor(),
                                           download=True)
# toTensor()将shape为(H, W, C)的numpy.ndarray或img转为shape为(C, H, W)的tensor
# 其将每一个数值归一化到[0,1]，其归一化方法比较简单，直接除以255即可

test_dataset = torchvision.datasets.MNIST(root='../../data',
                                          train=False,
                                          transform=transforms.ToTensor())

# Data loader (input pipeline)
# 参数：
# dataset (Dataset) – 加载数据的数据集
# batch_size (int, optional) – 每个batch加载多少个样本(默认: 1)
# shuffle (bool, optional) – 设置为True时会在每个epoch重新打乱数据(默认: False)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size,
                                          shuffle=False)

# Logistic regression model
model = nn.Linear(input_size, num_classes)

# Loss and optimizer
# nn.CrossEntropyLoss() computes softmax internally
# 该损失函数结合了nn.LogSoftmax()和nn.NLLLoss()两个函数。
# 在训练过程中，对于每个类分配权值，可选的参数权值应该是一个1D张量。
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        # Reshape images to (batch_size, input_size)
        images = images.reshape(-1, input_size)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i + 1) % 100 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                  .format(epoch + 1, num_epochs, i + 1, total_step, loss.item()))

# Test the model
# In test phase, we don't need to compute gradients (for memory efficiency)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, input_size)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)  # 解析：https://blog.csdn.net/weixin_48249563/article/details/111387501
        total += labels.size(0)
        correct += (predicted == labels).sum()

    print('Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')