تصنيف وجوه الحيوانات الأليفة

# Generated pet images for deterministic, rights-safe execution.
from pathlib import Path
from PIL import Image
import numpy as np

image_root = Path("images")
image_root.mkdir(parents=True, exist_ok=True)
for breed_index, breed in enumerate(("Abyssinian", "Maine_Coon", "beagle", "pug")):
    for image_index in range(1, 4):
        yy, xx = np.mgrid[:64, :64]
        pixels = np.zeros((64, 64, 3), dtype=np.uint8)
        pixels[..., 0] = (xx * (2 + breed_index) + 23 * image_index) % 256
        pixels[..., 1] = (yy * (3 + image_index) + 31 * breed_index) % 256
        pixels[..., 2] = ((xx + yy) * 2 + 47 * breed_index) % 256
        Image.fromarray(pixels).save(image_root / f"{breed}_{image_index}.jpg")
print("Prepared 12 generated pet images")

import matplotlib.pyplot as plt
import os
from PIL import Image
import numpy as np

def display_images(images, titles=None, fontsize=12):
    images = list(images)[:24]
    if not images:
        return
    columns = min(len(images), 6)
    rows = (len(images) + columns - 1) // columns
    fig, axes = plt.subplots(rows, columns, squeeze=False, figsize=(columns * 2.5, rows * 2.5))
    flat_axes = axes.reshape(-1)
    for index, image in enumerate(images):
        flat_axes[index].imshow(image)
        flat_axes[index].axis("off")
        if titles is not None and index < len(titles):
            flat_axes[index].set_title(titles[index], fontsize=fontsize)
    for axis in flat_axes[len(images):]:
        axis.axis("off")
    plt.tight_layout()
    plt.show()

# Note: The Oxford-IIIT Pet Dataset extracts to a folder named 'images'
# Images are named by breed (e.g., 'Abyssinian_1.jpg')
# We need to organize them into breed-specific subdirectories
import os
from collections import defaultdict

# Organize images by breed
if not os.path.exists('petfaces'):
    os.makedirs('petfaces')
    for img_file in os.listdir('images'):
        if img_file.endswith(('.jpg', '.png')):
            # Extract breed name from filename (everything before the last underscore and number)
            breed = '_'.join(img_file.split('_')[:-1])
            breed_dir = os.path.join('petfaces', breed)
            if not os.path.exists(breed_dir):
                os.makedirs(breed_dir)
            os.rename(os.path.join('images', img_file), os.path.join(breed_dir, img_file))

for cls in os.listdir('petfaces'):
    print(cls)
    display_images([Image.open(os.path.join('petfaces',cls,x))
                    for x in os.listdir(os.path.join('petfaces',cls))[:10]])

num_classes = len(os.listdir('petfaces'))
num_classes

# CODE TO LOAD DATASET

# CODE TO DO TRAIN/TEST SPLIT

# Print tensor sizes

# Display the data

# CODE TO DEFINE NEURAL NETWORK

# TRAIN THE NETWORK

# PLOT THE ACCURACY on train and validation dataset

# CALCULATE TOP-3 ACCURACY

# Define dataset that contains only two labels: 0 = cat, 1 = dog
# Hint: use class name prefix to figure out which one is which

# Define neural network architecture and train