pytorch_example.py

# Generated by ChatGPT with the following prompt:
# "write a simple pytorch program to solve mnist with a small MLP. use cuda."

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torchvision import datasets, transforms
from torch.utils.data import DataLoader

# Check if CUDA is available, and if so, use it
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Hyperparameters
batch_size = 64
learning_rate = 0.01
num_epochs = 5

# MNIST dataset and dataloaders
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,), (0.3081,))  # Normalize with mean and std of MNIST dataset
])

train_dataset = datasets.MNIST(root='./data', train=True, transform=transform, download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=transform, download=True)

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

# Define a simple MLP model
class MLP(nn.Module):
    def __init__(self):
        super(MLP, self).__init__()
        self.fc1 = nn.Linear(28 * 28, 256)  # Input layer
        self.fc2 = nn.Linear(256, 128)     # Hidden layer
        self.fc3 = nn.Linear(128, 10)      # Output layer

    def forward(self, x):
        x = x.view(-1, 28 * 28)  # Flatten the input
        x = F.relu(self.fc1(x))  # Apply ReLU activation
        x = F.relu(self.fc2(x))  # Apply ReLU activation
        x = self.fc3(x)          # Output layer
        return x

# Instantiate the model, define the loss function and the optimizer
model = MLP().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)

# Training loop
for epoch in range(num_epochs):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        
        # Forward pass
        outputs = model(data)
        loss = criterion(outputs, target)
        
        # Backward pass and optimization
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        if (batch_idx + 1) % 100 == 0:
            print(f'Epoch [{epoch+1}/{num_epochs}], Step [{batch_idx+1}/{len(train_loader)}], Loss: {loss.item():.4f}')

# Evaluation on test set
model.eval()
correct = 0
total = 0
with torch.no_grad():
    for data, target in test_loader:
        data, target = data.to(device), target.to(device)
        outputs = model(data)
        _, predicted = torch.max(outputs.data, 1)
        total += target.size(0)
        correct += (predicted == target).sum().item()

print(f'Test Accuracy: {100 * correct / total:.2f}%')