train_dclr_model.py

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

# Import the DCLR optimizer from the local file
from dclr_optimizer import DCLR

# === Simple CNN Model Definition ===
class SimpleCNN(nn.Module):
    def __init__(self):
        super(SimpleCNN, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, 3, padding=1)
        self.conv2 = nn.Conv2d(32, 64, 3, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(64 * 8 * 8, 512)
        self.fc2 = nn.Linear(512, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 64 * 8 * 8)
        x = F.relu(self.fc1(x))
        return self.fc2(x)

# === CIFAR-10 Data Loading ===
transform = transforms.Compose([transforms.ToTensor()])

train_set = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
train_loader = DataLoader(train_set, batch_size=128, shuffle=True)

# === Training Configuration ===
model = SimpleCNN()

# Instantiate DCLR with best-tuned hyperparameters
best_lr = 0.1
best_lambda = 0.1
optimizer = DCLR(model.parameters(), lr=best_lr, lambda_=best_lambda, verbose=False)

criterion = nn.CrossEntropyLoss()
extended_epochs = 20

print(f"Starting training for SimpleCNN with DCLR (lr={best_lr}, lambda_={best_lambda}) for {extended_epochs} epochs...")

# === Training Loop ===
for epoch in range(extended_epochs):
    model.train()
    running_loss = 0.0
    correct = 0
    total = 0
    for batch_idx, (inputs, labels) in enumerate(train_loader):
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()

        # DCLR requires output_activations for its step method
        optimizer.step(output_activations=outputs)

        running_loss += loss.item()
        _, predicted = outputs.max(1)
        total += labels.size(0)
        correct += predicted.eq(labels).sum().item()

    epoch_loss = running_loss / len(train_loader)
    epoch_acc = 100.0 * correct / total
    print(f"Epoch {epoch+1}/{extended_epochs} - Loss: {epoch_loss:.4f}, Accuracy: {epoch_acc:.2f}%")

print("Training complete.")

# === Save the Trained Model ===
torch.save(model.state_dict(), 'simple_cnn_dclr_tuned.pth')
print("Model saved to simple_cnn_dclr_tuned.pth")