autoencoder_inf.py

import torch
from torchvision import transforms
from PIL import Image
import matplotlib.pyplot as plt
from model import aeModel

def load_model(model_path, device):
    model = aeModel().to(device)
    model.load_state_dict(torch.load(model_path, map_location=device))
    model.eval()
    return model

def process_single_image(image_path, model, device):
    transform = transforms.Compose([
        transforms.Resize((64, 64)),
        transforms.ToTensor(),
    ])
    
    image = Image.open(image_path).convert('RGB')
    image_tensor = transform(image).unsqueeze(0).to(device)

    with torch.no_grad():
        encoded = model.encode(image_tensor)
        reconstruction = model.decode(encoded)
        
        print(f'Original shape: {image_tensor.shape}')
        print(f'Encoded shape: {encoded.shape}')
        print(f'Decoded shape: {reconstruction.shape}')

    return image_tensor.squeeze(0).cpu(), reconstruction.squeeze(0).cpu()

def visualize_original_and_reconstruction(original, reconstruction):
    original = torch.clamp(original, 0, 1)
    reconstruction = torch.clamp(reconstruction, 0, 1)
    
    fig, axes = plt.subplots(1, 2, figsize=(8, 4))
    
    axes[0].imshow(original.permute(1, 2, 0))
    axes[0].set_title("Original")
    axes[0].axis("off")
    
    axes[1].imshow(reconstruction.permute(1, 2, 0))
    axes[1].set_title("Decoded")
    axes[1].axis("off")
    
    plt.tight_layout()
    plt.show()


if __name__ == "__main__":
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    print(f"Using device: {device}")

    model_path = 'autoencoder.pth'
    model = load_model(model_path, device)

    image_path = r"dataset\images\proof_2.png"
 
    original, reconstruction = process_single_image(image_path, model, device)
    visualize_original_and_reconstruction(original, reconstruction)