{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":21755,"databundleVersionId":1475600,"sourceType":"competition"},{"sourceId":12047014,"sourceType":"datasetVersion","datasetId":7581269}],"dockerImageVersionId":31040,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# !pip install tensorflow==2.15.0\n# !pip install tensorflow-addons","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-04T07:09:23.892025Z","iopub.execute_input":"2025-06-04T07:09:23.892691Z","iopub.status.idle":"2025-06-04T07:09:23.895700Z","shell.execute_reply.started":"2025-06-04T07:09:23.892659Z","shell.execute_reply":"2025-06-04T07:09:23.895102Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\nimport tensorflow_addons as tfa\nfrom tensorflow import keras\nfrom tensorflow.keras import layers, Model\nfrom tensorflow.keras.preprocessing.image import load_img, img_to_array\n\nimport os\nimport cv2\nimport shutil\nimport random\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib.ticker import FuncFormatter\nimport zipfile\nimport sys\nfrom PIL import Image\nfrom PIL import Image, ImageChops, ImageEnhance, ImageFilter\nfrom skimage.metrics import structural_similarity as ssim","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-04T07:09:28.358817Z","iopub.execute_input":"2025-06-04T07:09:28.359372Z","iopub.status.idle":"2025-06-04T07:09:28.362684Z","shell.execute_reply.started":"2025-06-04T07:09:28.359344Z","shell.execute_reply":"2025-06-04T07:09:28.362040Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"try:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    print('Device:', tpu.master())\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.TPUStrategy(tpu)\nexcept:\n    strategy = tf.distribute.get_strategy()\nprint('Number of replicas:', strategy.num_replicas_in_sync)\n\nAUTOTUNE = tf.data.experimental.AUTOTUNE\n\nprint('Tensorflow : ',tf.__version__)\nprint('Python : ',sys.version.split()[0])\n\nmonet_jpg_directory = '/kaggle/input/gan-getting-started/monet_jpg'\nphoto_jpg_directory = '/kaggle/input/gan-getting-started/photo_jpg'","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-04T06:43:52.711245Z","iopub.status.idle":"2025-06-04T06:43:52.711872Z","shell.execute_reply.started":"2025-06-04T06:43:52.711424Z","shell.execute_reply":"2025-06-04T06:43:52.711438Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def tampilkan_20_gambar(input_dir, title=\"\"):\n    file_list = [f for f in os.listdir(input_dir) if f.lower().endswith(('.jpg', '.jpeg', '.png'))][:20]\n    plt.figure(figsize=(20, 5))\n    for i, file_name in enumerate(file_list):\n        img_path = os.path.join(input_dir, file_name)\n        with Image.open(img_path) as img:\n            plt.subplot(2, 10, i + 1)\n            plt.imshow(img)\n            plt.axis('off')\n\n    plt.suptitle(title, fontsize=16)\n    plt.tight_layout()\n    plt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"tampilkan_20_gambar(photo_jpg_directory)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"tampilkan_20_gambar(monet_jpg_directory)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def load_image_from_directory(directory, image_index=0, target_size=(256, 256)):\n    image_files = [f for f in os.listdir(directory) if f.lower().endswith(('jpg', 'jpeg', 'png'))]\n    image_path = os.path.join(directory, image_files[image_index])\n    img = Image.open(image_path).convert('RGB')\n    img = img.resize(target_size)\n    img_array = np.array(img) / 255.0 \n    return img_array\n\ndef visualize_RGB_distribution(image_array, title):\n    img = (image_array * 255).astype(np.uint8)\n\n    plt.figure(figsize=(12, 4))\n    plt.subplot(1, 4, 1)\n    plt.title(title)\n    plt.imshow(img)\n    plt.axis('off')\n\n    colors = ['red', 'green', 'blue']\n    for i, color in enumerate(colors):\n        plt.subplot(1, 4, i + 2)\n        plt.title(f'{color.capitalize()} Channel')\n        plt.hist(img[:, :, i].flatten(), bins=50, color=color, alpha=0.7)\n        plt.xlim([0, 255])\n    plt.tight_layout()\n    plt.show()\n\nmonet_image = load_image_from_directory(monet_jpg_directory)\nphoto_image = load_image_from_directory(photo_jpg_directory)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"visualize_RGB_distribution(monet_image, 'Monet Painting Color Distribution')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"visualize_RGB_distribution(photo_image, 'Photo Color Distribution')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def getImagePaths(path):\n    image_names = []\n    for dirname, _, filenames in os.walk(path):\n        for filename in filenames:\n            fullpath = os.path.join(dirname, filename)\n            image_names.append(fullpath)\n    return image_names\n\nmonet_images_path = getImagePaths(monet_jpg_directory)\nphoto_images_path = getImagePaths(photo_jpg_directory)\n\nprint(f\"Number of Monet images: {len(monet_images_path)}\")\nprint(f\"Number of Photo images: {len(photo_images_path)}\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def preprocess_image(image_path):\n    image = tf.io.read_file(image_path)\n    image = tf.image.decode_jpeg(image, channels=3)\n    image = tf.cast(image, tf.float32)\n    image = (image / 127.5) - 1 \n    return image\n\nmonet_ds = tf.data.Dataset.from_tensor_slices(monet_images_path).map(preprocess_image, num_parallel_calls=AUTOTUNE)\nphoto_ds = tf.data.Dataset.from_tensor_slices(photo_images_path).map(preprocess_image, num_parallel_calls=AUTOTUNE)\n\nBATCH_SIZE = 8\nmonet_ds = monet_ds.cache().shuffle(1000).batch(BATCH_SIZE).prefetch(AUTOTUNE)\nphoto_ds = photo_ds.cache().shuffle(1000).batch(BATCH_SIZE).prefetch(AUTOTUNE)\n\ndef downsample(filters, size, apply_instancenorm=True):\n    initializer = tf.random_normal_initializer(0., 0.02)\n    result = tf.keras.Sequential()\n    result.add(layers.Conv2D(filters, size, strides=2, padding='same',kernel_initializer=initializer, use_bias=False))\n    if apply_instancenorm:\n        result.add(tfa.layers.InstanceNormalization())\n    result.add(layers.LeakyReLU())\n    return result\n\ndef upsample(filters, size, apply_dropout=False):\n    initializer = tf.random_normal_initializer(0., 0.02)\n    result = tf.keras.Sequential()\n    result.add(layers.Conv2DTranspose(filters, size, strides=2, padding='same',kernel_initializer=initializer, use_bias=False))\n    result.add(tfa.layers.InstanceNormalization())\n    if apply_dropout:\n        result.add(layers.Dropout(0.5))\n    result.add(layers.ReLU())\n    return result","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def Generator():\n    inputs = layers.Input(shape=[256, 256, 3])\n    \n    down_stack = [\n        downsample(64, 4, apply_instancenorm=False), \n        downsample(128, 4), \n        downsample(256, 4),  \n        downsample(512, 4),  \n        downsample(512, 4),  \n        downsample(512, 4),  \n        downsample(512, 4),  \n        downsample(512, 4),  \n    ]\n    \n    res_blocks = [layers.Conv2D(512, 3, strides=1, padding='same', activation='relu', \n                                kernel_initializer=tf.random_normal_initializer(0., 0.02)) for _ in range(2)]\n    \n    up_stack = [\n        upsample(512, 4, apply_dropout=True),  \n        upsample(512, 4, apply_dropout=True),  \n        upsample(512, 4, apply_dropout=True),  \n        upsample(512, 4),  \n        upsample(256, 4),  \n        upsample(128, 4),  \n        upsample(64, 4),  \n    ]\n    \n    initializer = tf.random_normal_initializer(0., 0.02)\n    last = layers.Conv2DTranspose(3, 4, strides=2, padding='same',kernel_initializer=initializer, activation='tanh')  \n    \n    x = inputs\n    skips = []\n    for down in down_stack:\n        x = down(x)\n        skips.append(x)\n    \n    for res in res_blocks:\n        x = res(x)\n    \n    skips = reversed(skips[:-1])\n    for up, skip in zip(up_stack, skips):\n        x = up(x)\n        x = layers.Concatenate()([x, skip])\n    \n    x = last(x)\n    return Model(inputs=inputs, outputs=x)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def Discriminator():\n    initializer = tf.random_normal_initializer(0., 0.02)\n    inp = layers.Input(shape=[256, 256, 3], name='input_image')\n    x = inp\n    \n    down1 = downsample(64, 4, False)(x)  \n    down2 = downsample(128, 4)(down1)  \n    down3 = downsample(256, 4)(down2)  \n    \n    zero_pad1 = layers.ZeroPadding2D()(down3)  \n    conv = layers.Conv2D(512, 4, strides=1, kernel_initializer=initializer,use_bias=False)(zero_pad1)  \n    norm1 = tfa.layers.InstanceNormalization()(conv)\n    leaky_relu = layers.LeakyReLU()(norm1)\n    zero_pad2 = layers.ZeroPadding2D()(leaky_relu)  \n    last = layers.Conv2D(1, 4, strides=1, kernel_initializer=initializer)(zero_pad2) \n    \n    return Model(inputs=inp, outputs=last)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"strategy = tf.distribute.MirroredStrategy()\nwith strategy.scope():\n    monet_generator = Generator()\n    photo_generator = Generator()\n    monet_discriminator = Discriminator()\n    photo_discriminator = Discriminator()\n\nwith strategy.scope():\n    loss_obj = tf.keras.losses.BinaryCrossentropy(from_logits=True, reduction=tf.keras.losses.Reduction.NONE)\n\ndef discriminator_loss(real, generated):\n    real_loss = tf.reduce_mean(loss_obj(tf.ones_like(real), real))\n    generated_loss = tf.reduce_mean(loss_obj(tf.zeros_like(generated), generated))\n    total_disc_loss = real_loss + generated_loss\n    return total_disc_loss * 0.5\n\ndef generator_loss(generated):\n    return tf.reduce_mean(loss_obj(tf.ones_like(generated), generated))\n\ndef calc_cycle_loss(real_image, cycled_image, LAMBDA=10):  \n    l1_loss = tf.reduce_mean(tf.abs(real_image - cycled_image))\n    l2_loss = tf.reduce_mean(tf.square(real_image - cycled_image))\n    return LAMBDA * (0.9 * l1_loss + 0.1 * l2_loss)  \n\ndef identity_loss(real_image, same_image, LAMBDA=5): \n    loss = tf.reduce_mean(tf.abs(real_image - same_image))\n    return LAMBDA * 0.5 * loss\n\ninitial_learning_rate = 2e-4\nlr_schedule = tf.keras.optimizers.schedules.PiecewiseConstantDecay(\n    boundaries=[50 * (len(monet_images_path) // BATCH_SIZE), 75 * (len(monet_images_path) // BATCH_SIZE)],\n    values=[initial_learning_rate, initial_learning_rate * 0.1, initial_learning_rate * 0.01]\n)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"with strategy.scope():\n    monet_generator_optimizer = tf.keras.optimizers.Adam(learning_rate=lr_schedule, beta_1=0.5, clipnorm=1.0)\n    photo_generator_optimizer = tf.keras.optimizers.Adam(learning_rate=lr_schedule, beta_1=0.5, clipnorm=1.0)\n    monet_discriminator_optimizer = tf.keras.optimizers.Adam(learning_rate=lr_schedule, beta_1=0.5, clipnorm=1.0)\n    photo_discriminator_optimizer = tf.keras.optimizers.Adam(learning_rate=lr_schedule, beta_1=0.5, clipnorm=1.0)\n\n@tf.function\ndef train_step(real_monet, real_photo):\n    with tf.GradientTape(persistent=True) as tape:\n        fake_monet = monet_generator(real_photo, training=True)\n        cycled_photo = photo_generator(fake_monet, training=True)\n        fake_photo = photo_generator(real_monet, training=True)\n        cycled_monet = monet_generator(fake_photo, training=True)\n        same_monet = monet_generator(real_monet, training=True)\n        same_photo = photo_generator(real_photo, training=True)\n        disc_real_monet = monet_discriminator(real_monet, training=True)\n        disc_real_photo = photo_discriminator(real_photo, training=True)\n        disc_fake_monet = monet_discriminator(fake_monet, training=True)\n        disc_fake_photo = photo_discriminator(fake_photo, training=True)\n        monet_gen_loss = generator_loss(disc_fake_monet)\n        photo_gen_loss = generator_loss(disc_fake_photo)\n        total_cycle_loss = calc_cycle_loss(real_monet, cycled_monet) + calc_cycle_loss(real_photo, cycled_photo)\n        total_monet_gen_loss = monet_gen_loss + total_cycle_loss + identity_loss(real_monet, same_monet)\n        total_photo_gen_loss = photo_gen_loss + total_cycle_loss + identity_loss(real_photo, same_photo)\n        monet_disc_loss = discriminator_loss(disc_real_monet, disc_fake_monet)\n        photo_disc_loss = discriminator_loss(disc_real_photo, disc_fake_photo)\n    \n    monet_generator_gradients = tape.gradient(total_monet_gen_loss, monet_generator.trainable_variables)\n    photo_generator_gradients = tape.gradient(total_photo_gen_loss, photo_generator.trainable_variables)\n    monet_discriminator_gradients = tape.gradient(monet_disc_loss, monet_discriminator.trainable_variables)\n    photo_discriminator_gradients = tape.gradient(photo_disc_loss, photo_discriminator.trainable_variables)\n    \n    monet_generator_optimizer.apply_gradients(zip(monet_generator_gradients, monet_generator.trainable_variables))\n    photo_generator_optimizer.apply_gradients(zip(photo_generator_gradients, photo_generator.trainable_variables))\n    monet_discriminator_optimizer.apply_gradients(zip(monet_discriminator_gradients, monet_discriminator.trainable_variables))\n    photo_discriminator_optimizer.apply_gradients(zip(photo_discriminator_gradients, photo_discriminator.trainable_variables))\n    \n    return total_monet_gen_loss, total_photo_gen_loss, monet_disc_loss, photo_disc_loss","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history = { \n    'monet_gen_loss': [],\n    'photo_gen_loss': [],\n    'monet_disc_loss': [],\n    'photo_disc_loss': [] \n}\n\nEPOCHS = 50\nfor epoch in range(EPOCHS):\n    print(f\"Epoch {epoch + 1}/{EPOCHS}\")\n    total_monet_gen_loss = 0\n    total_photo_gen_loss = 0\n    total_monet_disc_loss = 0\n    total_photo_disc_loss = 0\n    n_batches = 0\n\n    for real_monet, real_photo in tf.data.Dataset.zip((monet_ds, photo_ds)):\n        monet_gen_loss, photo_gen_loss, monet_disc_loss, photo_disc_loss = train_step(real_monet, real_photo)\n        total_monet_gen_loss += monet_gen_loss.numpy()\n        total_photo_gen_loss += photo_gen_loss.numpy()\n        total_monet_disc_loss += monet_disc_loss.numpy()\n        total_photo_disc_loss += photo_disc_loss.numpy()\n        n_batches += 1\n\n    avg_monet_gen_loss = total_monet_gen_loss / n_batches\n    avg_photo_gen_loss = total_photo_gen_loss / n_batches\n    avg_monet_disc_loss = total_monet_disc_loss / n_batches\n    avg_photo_disc_loss = total_photo_disc_loss / n_batches\n\n    history['monet_gen_loss'].append(avg_monet_gen_loss)\n    history['photo_gen_loss'].append(avg_photo_gen_loss)\n    history['monet_disc_loss'].append(avg_monet_disc_loss)\n    history['photo_disc_loss'].append(avg_photo_disc_loss)\n\n    print(f\"Avg Monet Gen Loss: {avg_monet_gen_loss:.4f}, Avg Photo Gen Loss: {avg_photo_gen_loss:.4f}, \"\n          f\"Avg Monet Disc Loss: {avg_monet_disc_loss:.4f}, Avg Photo Disc Loss: {avg_photo_disc_loss:.4f}\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def plot_generator_losses_side_by_side(history):\n    plt.figure(figsize=(16, 6))\n\n    plt.subplot(1, 2, 1)\n    plt.plot(history['monet_gen_loss'], label='Monet Generator Loss', color='orange')\n    plt.xlabel('Epoch')\n    plt.ylabel('Loss')\n    plt.title('Monet Generator Loss')\n    plt.legend()\n    plt.grid(True)\n\n    plt.subplot(1, 2, 2)\n    plt.plot(history['photo_gen_loss'], label='Photo Generator Loss', color='blue')\n    plt.xlabel('Epoch')\n    plt.ylabel('Loss')\n    plt.title('Photo Generator Loss')\n    plt.legend()\n    plt.grid(True)\n\n    plt.tight_layout()\n    plt.show()\n\nplot_generator_losses_side_by_side(history)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def plot_discriminator_losses_side_by_side(history):\n    plt.figure(figsize=(16, 6))\n\n    plt.subplot(1, 2, 1)\n    plt.plot(history['monet_disc_loss'], label='Monet Discriminator Loss', color='orange')\n    plt.xlabel('Epoch')\n    plt.ylabel('Loss')\n    plt.title('Monet Discriminator Loss')\n    plt.legend()\n    plt.grid(True)\n\n    plt.subplot(1, 2, 2)\n    plt.plot(history['photo_disc_loss'], label='Photo Discriminator Loss', color='blue')\n    plt.xlabel('Epoch')\n    plt.ylabel('Loss')\n    plt.title('Photo Discriminator Loss')\n    plt.legend()\n    plt.grid(True)\n\n    plt.tight_layout()\n    plt.show()\n\nplot_discriminator_losses_side_by_side(history)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def display_generated_images(photo_ds, num_images=5, start_from=1):\n    plt.figure(figsize=(20, 6)) \n    ssim_scores = []\n\n    selected_photos = photo_ds.skip(start_from - 1).take(num_images)\n\n    for i, photo in enumerate(selected_photos):\n        fake_monet = monet_generator(photo, training=False)\n\n        fake_monet_rescaled = (fake_monet[0] * 0.5 + 0.5).numpy()\n        photo_rescaled = (photo[0] * 0.5 + 0.5).numpy()\n\n        ssim_score = tf.image.ssim(photo_rescaled, fake_monet_rescaled, max_val=1.0).numpy()\n        ssim_percent = ssim_score * 100\n        ssim_scores.append(ssim_percent)\n\n        plt.subplot(2, num_images, i + 1)\n        plt.imshow(photo_rescaled)\n        plt.title(f\"Photo {start_from + i}\")\n        plt.axis('off')\n\n        plt.subplot(2, num_images, i + 1 + num_images)\n        plt.imshow(fake_monet_rescaled)\n        plt.title(f\"Monet Style\\nSSIM: {ssim_percent:.2f}%\")\n        plt.axis('off')\n\n    mean_ssim = sum(ssim_scores) / len(ssim_scores)\n    print(f\"📊 Rata-rata SSIM : {mean_ssim:.2f}%\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"display_generated_images(photo_ds, num_images=5, start_from=1)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_dir = '/kaggle/input/images'\nimage_paths = []\n\nfor root, dirs, files in os.walk(image_dir):\n    for file in files:\n        if file.endswith('.jpg') or file.endswith('.png'):\n            image_paths.append(os.path.join(root, file))\n\nprint(f\"Total images : {len(image_paths)}\") \n\n\noutput_dir = '/kaggle/working/images'\nos.makedirs(output_dir, exist_ok=True)\n\nfor path in image_paths:\n    shutil.copy(path, output_dir)\n\n\nzip_path = '/kaggle/working/images.zip'\nwith zipfile.ZipFile(zip_path, 'w') as zipf:\n    for file in os.listdir(output_dir):\n        zipf.write(os.path.join(output_dir, file), arcname=file)","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}