VitePress

Appearance

PyTorch ​

Open-source machine learning framework.

Overview ​

PyTorch is an open source machine learning framework based on the Torch library, used for applications such as computer vision and natural language processing.

Features ​

  • Dynamic computation graphs
  • Tensor computations
  • Neural network modules
  • Automatic differentiation
  • GPU acceleration
  • TorchScript for deployment

Getting Started ​

bash
pip install torch torchvision

Basic Example ​

python
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset

# Define a neural network
class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(784, 512),
            nn.ReLU(),
            nn.Dropout(0.2),
            nn.Linear(512, 256),
            nn.ReLU(),
            nn.Dropout(0.2),
            nn.Linear(256, 10)
        )
    
    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

# Create model instance
model = NeuralNetwork()
print(model)

# Generate dummy data
X = torch.randn(1000, 784)
y = torch.randint(0, 10, (1000,))
dataset = TensorDataset(X, y)
dataloader = DataLoader(dataset, batch_size=32, shuffle=True)

# Training setup
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# Training loop
for epoch in range(5):
    for batch_idx, (data, target) in enumerate(dataloader):
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()
    
    print(f'Epoch {epoch+1}, Loss: {loss.item():.4f}')

# Make predictions
model.eval()
with torch.no_grad():
    sample = torch.randn(1, 784)
    prediction = model(sample)
    predicted_class = torch.argmax(prediction, dim=1)
    print(f'Predicted class: {predicted_class.item()}')

PAPER-CODE Integration ​

PAPER-CODE provides:

  • PyTorch project templates
  • Model architectures
  • Training pipelines
  • Deployment configurations

Resources ​