logistic regression

import torch
import torch.nn as nn
import torchvision # 包含目前流行的数据集、模型结构和常用的图片
import torchvision.transforms as transforms


"""
1. 设置超参数
2. 下载数据，加载数据
3. 加载模型
4. 定义损失函数和优化器
5. 开始训练
6. 测试模型
7. 保存模型
"""

# Hyper-parameters 设置超参数
input_size = 784
num_classes = 10
num_epochs = 5
batch_size = 100
learning_rate = 0.001


# MNIST dataset (images and labels) 下载数据
train_dataset = torchvision.datasets.MNIST(root='../data', train=True,transform=transforms.ToTensor(),download=True)
print(type(train_dataset))
test_dataset = torchvision.datasets.MNIST(root='../data', train=False,transform=transforms.ToTensor())

# Data loader (input pipeline) 加载数据
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,batch_size=batch_size,shuffle=True)
print(type(train_loader))

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

# Logistic regression model  加载模型
model = nn.Linear(input_size, num_classes)  # 对于模型，输入是数据，输出是分的类别数

# Loss and optimizer
# nn.CrossEntropyLoss() computes softmax internally  定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

# Train the model   开始训练
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, 28*28)

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

        # Backward and optimize
        optimizer.zero_grad() # 梯度归零
        loss.backward()   # 反向传播求梯度
        optimizer.step()  # 更新所有参数

        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, 28*28)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        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')