PyTorch Neural Networks

Introduction

PyTorch uses nn.Module to define neural networks with forward() and automatic backpropagation.

Basic Network

import torch
import torch.nn as nn

class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(784, 256)
        self.fc2 = nn.Linear(256, 128)
        self.fc3 = nn.Linear(128, 10)
        self.relu = nn.ReLU()
        self.dropout = nn.Dropout(0.2)

    def forward(self, x):
        x = x.view(-1, 784)  # Flatten
        x = self.relu(self.fc1(x))
        x = self.dropout(x)
        x = self.relu(self.fc2(x))
        x = self.fc3(x)
        return x

model = SimpleNet()
print(model)

CNN

class CNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=3)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)
        self.pool = nn.MaxPool2d(2)
        self.fc = nn.Linear(64 * 5 * 5, 10)

    def forward(self, x):
        x = self.pool(torch.relu(self.conv1(x)))
        x = self.pool(torch.relu(self.conv2(x)))
        x = x.view(-1, 64 * 5 * 5)
        return self.fc(x)

RNN

class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers):
        super().__init__()
        self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size, 10)

    def forward(self, x):
        out, hidden = self.rnn(x)
        return self.fc(out[:, -1, :])

Forward and Backward

model = SimpleNet()
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

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

# Backward pass
optimizer.zero_grad()
loss.backward()
optimizer.step()

Practice Problems

1. Build feedforward network
2. Create CNN for images
3. Implement RNN for sequences
4. Use different activation functions
5. Add custom layers