train_font_identifier.py

import copy
import os
import time
import torch
import torch.optim as optim
from torch.optim import lr_scheduler
from torchvision import datasets, models, transforms
from tqdm import tqdm

# Directory with organized font images
data_dir = './train_test_images'

# Define transformations for the image data
data_transforms = {
    'train': transforms.Compose([
        transforms.Resize((224, 224)),  # Resize to the input size expected by the model
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])  # ImageNet standards
    ]),
    'test': transforms.Compose([
        transforms.Resize((224, 224)),  # Resize to the input size expected by the model
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}


# Create datasets
image_datasets = {
    x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])
    for x in ['train', 'test']
}

# Create dataloaders
dataloaders = {
    'train': torch.utils.data.DataLoader(image_datasets['train'], batch_size=4),
    'test': torch.utils.data.DataLoader(image_datasets['test'], batch_size=4)
}

# Define the model
model = models.resnet18(weights=models.ResNet18_Weights.DEFAULT)

# Define the loss function
criterion = torch.nn.CrossEntropyLoss()

# Optimizer (you can replace 'model.parameters()' with specific parameters to optimize if needed)
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)

# Number of epochs to train for
num_epochs = 25

def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase
        for phase in ['train', 'test']:
            if phase == 'train':
                model.train()  # Set model to training mode
            else:
                model.eval()   # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            # Here we wrap the dataloader with tqdm for a progress bar
            for inputs, labels in tqdm(dataloaders[phase], desc=f"Epoch {epoch} - {phase}"):
                # Zero the parameter gradients
                optimizer.zero_grad()

                # Forward
                # Track history if only in train
                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # Backward + optimize only if in training phase
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # Statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)
            if phase == 'train':
                scheduler.step()

            epoch_loss = running_loss / len(image_datasets[phase])
            epoch_acc = running_corrects.double() / len(image_datasets[phase])

            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # Deep copy the model
            if phase == 'test' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())

        print()

    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
    print('Best test Acc: {:4f}'.format(best_acc))

    # Load best model weights
    model.load_state_dict(best_model_wts)
    return model

# Train the model
model = train_model(model, criterion, optimizer, exp_lr_scheduler, num_epochs=num_epochs)