3.Logistic Regression

the difference of logistc regression and linear regression is the code of :

# Linear regression model 一个输入一个输出
model = nn.Linear(1, 1)

# Logistic regression model 多个输入，多个输出
model = nn.Linear(28*28, 10) 

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

# Data loader (input pipeline)
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) # (28*28, 10)

# Loss and optimizer
# nn.CrossEntropyLoss() computes softmax internally
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)  # (100,784)

        # Forward pass
        outputs = model(images)             # outputs.size(): ([100, 10])
        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)
        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')

pytorch-tutorial/main.py at master · yunjey/pytorch-tutorial · GitHub