Update train_dclr_model.py

train_dclr_model.py

@@ -0,0 +1,75 @@
+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")