任务7 手写数字识别

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

device = torch.device("cpu")

# Hyper-parameters 
input_size = 784
hidden_size = 500
num_classes = 10
num_epochs = 5
batch_size = 100
learning_rate = 0.001

# MNIST dataset 
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
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)

# Fully connected neural network with one hidden layer
class NeuralNet(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(NeuralNet, self).__init__()
        self.fc1 = nn.Linear(input_size, hidden_size) 
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(hidden_size, num_classes)  
    
    def forward(self, x):
        out = self.fc1(x)
        out = self.relu(out)
        out = self.fc2(out)
        return out

model = NeuralNet(input_size, hidden_size, num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(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):  
        # Move tensors to the configured device
        images = images.reshape(-1, 28 * 28).to(device)
        labels = labels.to(device)
        
        # 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, 28*28).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

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

Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz to data/MNIST\raw\train-images-idx3-ubyte.gz
100.1%
Extracting data/MNIST\raw\train-images-idx3-ubyte.gz
Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz to data/MNIST\raw\train-labels-idx1-ubyte.gz
113.5%
Extracting data/MNIST\raw\train-labels-idx1-ubyte.gz
Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz to data/MNIST\raw\t10k-images-idx3-ubyte.gz
100.4%
Extracting data/MNIST\raw\t10k-images-idx3-ubyte.gz
Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz to data/MNIST\raw\t10k-labels-idx1-ubyte.gz
180.4%
Extracting data/MNIST\raw\t10k-labels-idx1-ubyte.gz
Processing...
Done!
Epoch [1/5], Step [100/600], Loss: 0.5448
Epoch [1/5], Step [200/600], Loss: 0.2312
Epoch [1/5], Step [300/600], Loss: 0.1262
Epoch [1/5], Step [400/600], Loss: 0.1997
Epoch [1/5], Step [500/600], Loss: 0.1929
Epoch [1/5], Step [600/600], Loss: 0.1126
Epoch [2/5], Step [100/600], Loss: 0.1524
Epoch [2/5], Step [200/600], Loss: 0.1506
Epoch [2/5], Step [300/600], Loss: 0.0732
Epoch [2/5], Step [400/600], Loss: 0.1012
Epoch [2/5], Step [500/600], Loss: 0.0507
Epoch [2/5], Step [600/600], Loss: 0.0819
Epoch [3/5], Step [100/600], Loss: 0.0578
Epoch [3/5], Step [200/600], Loss: 0.0737
Epoch [3/5], Step [300/600], Loss: 0.0596
Epoch [3/5], Step [400/600], Loss: 0.0587
Epoch [3/5], Step [500/600], Loss: 0.0475
Epoch [3/5], Step [600/600], Loss: 0.0561
Epoch [4/5], Step [100/600], Loss: 0.0366
Epoch [4/5], Step [200/600], Loss: 0.0558
Epoch [4/5], Step [300/600], Loss: 0.0533
Epoch [4/5], Step [400/600], Loss: 0.0772
Epoch [4/5], Step [500/600], Loss: 0.0362
Epoch [4/5], Step [600/600], Loss: 0.0635
Epoch [5/5], Step [100/600], Loss: 0.0400
Epoch [5/5], Step [200/600], Loss: 0.0172
Epoch [5/5], Step [300/600], Loss: 0.0518
Epoch [5/5], Step [400/600], Loss: 0.0423
Epoch [5/5], Step [500/600], Loss: 0.0595
Epoch [5/5], Step [600/600], Loss: 0.0842
Accuracy of the network on the 10000 test images: 97.62 %