models/python/train.py

import os
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms, models
from torch.utils.data import DataLoader
from tqdm import tqdm
from pathlib import Path

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

# Paths
root_dir = Path("/oxford_pet_dataset")
train_dir = root_dir / "train"
val_dir = root_dir / "val"

# Parameters
BATCH_SIZE = 32
EPOCHS = 10
NUM_CLASSES = len(os.listdir(train_dir))  # Assumes one folder per class

# Transforms
train_transforms = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize([0.5]*3, [0.5]*3)
])

val_transforms = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize([0.5]*3, [0.5]*3)
])

# Datasets
train_dataset = datasets.ImageFolder(train_dir, transform=train_transforms)
val_dataset = datasets.ImageFolder(val_dir, transform=val_transforms)

# DataLoaders
train_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True)
val_loader = DataLoader(val_dataset, batch_size=BATCH_SIZE)

# Model
model = models.resnet18(pretrained=True)
model.fc = nn.Linear(model.fc.in_features, NUM_CLASSES)
model = model.to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=1e-4)

# Training loop
for epoch in range(EPOCHS):
    model.train()
    train_loss, train_correct = 0.0, 0

    for inputs, labels in tqdm(train_loader, desc=f"Epoch {epoch+1}/{EPOCHS} [Train]"):
        inputs, labels = inputs.to(device), labels.to(device)

        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        train_loss += loss.item() * inputs.size(0)
        train_correct += (outputs.argmax(1) == labels).sum().item()

    train_acc = train_correct / len(train_dataset)

    # Validation
    model.eval()
    val_loss, val_correct = 0.0, 0

    with torch.no_grad():
        for inputs, labels in tqdm(val_loader, desc=f"Epoch {epoch+1}/{EPOCHS} [Val]"):
            inputs, labels = inputs.to(device), labels.to(device)
            outputs = model(inputs)
            loss = criterion(outputs, labels)

            val_loss += loss.item() * inputs.size(0)
            val_correct += (outputs.argmax(1) == labels).sum().item()

    val_acc = val_correct / len(val_dataset)

    print(f"Epoch {epoch+1}: Train Acc: {train_acc:.4f}, Val Acc: {val_acc:.4f}")

# Save model
torch.save(model.state_dict(), "pet_classifier.pth")
print("Model saved as pet_classifier.pth")