train_torch.py

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, Dataset
from torchvision import transforms
from PIL import Image
import os

# Define the CNN architecture
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=3, padding=1)
        self.conv3 = nn.Conv2d(32, 64, kernel_size=3, padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(64 * 5 * 5, 128)
        self.fc2 = nn.Linear(128, 360)  # 360 classes for 0-359 degrees rotation

    def forward(self, x):
        x = self.pool(torch.relu(self.conv1(x)))
        x = self.pool(torch.relu(self.conv2(x)))
        x = self.pool(torch.relu(self.conv3(x)))
        x = x.view(-1, 64 * 5 * 5)
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# Define dataset class
class RotationDataset(Dataset):
    def __init__(self, root_dir, transform=None):
        self.root_dir = root_dir
        self.transform = transform
        self.image_files = sorted(os.listdir(root_dir))

    def __len__(self):
        return len(self.image_files)

    def __getitem__(self, idx):
        img_name = self.image_files[idx]
        img_path = os.path.join(self.root_dir, img_name)
        image = Image.open(img_path).convert('RGB')
        label = int(img_name.split('_')[-1].split('.')[0])  # Extract label from file name
        # Ensure label is within bounds
        label = label % 359  # Limit label to 0-358 range
        if self.transform:
            image = self.transform(image)
        return image, label

# Set device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Define transformations
transform = transforms.Compose([
    transforms.Resize((40, 40)),
    transforms.ToTensor(),
])

# Define dataset and dataloader
dataset = RotationDataset(root_dir='360', transform=transform)
dataloader = DataLoader(dataset, batch_size=64, shuffle=True)

# Initialize the model, loss function, and optimizer
model = CNN().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

# Training loop
num_epochs = 100
for epoch in range(num_epochs):
    running_loss = 0.0
    for i, data in enumerate(dataloader, 0):
        inputs, labels = data[0].to(device), data[1].to(device)

        # Zero the parameter gradients
        optimizer.zero_grad()

        # Forward + backward + optimize
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # Print statistics
        running_loss += loss.item()
        if i % 100 == 99:  # Print every 100 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 100))
            running_loss = 0.0

print('Finished Training')

# Save the model
torch.save(model.state_dict(), 'rotate_model.pth')