import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, Dataset
from consts import TRAIN_DATA
from tqdm import tqdm
from model import DogCatClassifier
from dogs_cats_ds import DogCatDataset

def train(model: nn.Module, train_loader: DataLoader, criterion, optimizer, device, epochs):
    model.to(device)
    model.train()

    for epoch in tqdm(range(epochs)):
        running_loss = 0.0
        correct = 0
        total = 0
        for i, (img, lab) in enumerate(train_loader):
            img, lab = img.to(device), lab.to(device).float().view(-1, 1)
            optimizer.zero_grad()

            out = model(img)
            loss = criterion(out, lab)
            loss.backward()
            optimizer.step()

            running_loss += loss.item()
            pred = (out > 0.5).float()
            total += lab.size(0)
            correct += (pred == lab).sum().item()

            if (i + 1) % 50:
                print(f'yo its epoch {epoch + 1} out of {epochs} and we on minibatch {i + 1} / {len(train_loader)}. Loss lookin like: {running_loss/100:.4f}, acc lookin like {100 * correct / total :.2f}%')
                running_loss = 0.0
                total = 0
                correct = 0


if __name__ == "__main__":
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    print(f'Using device: {device}')
    dog_train_dataset = DogCatDataset(TRAIN_DATA)
    dog_train_loader = DataLoader(dog_train_dataset, batch_size = 32, shuffle = True) # since its train, ok to shuffle
    model = DogCatClassifier()
    criterion = nn.BCELoss()
    optimizer = optim.Adam(model.parameters(), lr = 0.001)
    print(model)

    train(model = model, train_loader = dog_train_loader, criterion = criterion, optimizer = optimizer, device = device, epochs = 10)
    torch.save(model.state_dict(), 'dog_cat_classifier.pth')
    print('done w train, model saved')