{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":21755,"databundleVersionId":1475600,"sourceType":"competition"}],"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import tensorflow as tf\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport os\nimport time\nfrom IPython.display import clear_output\n\n\n# Define constants\nAUTOTUNE = tf.data.AUTOTUNE\nBUFFER_SIZE = 1000\nBATCH_SIZE = 3\nIMG_WIDTH = 256\nIMG_HEIGHT = 256\nLAMBDA = 30  # Cycle consistency loss weight\n","metadata":{"execution":{"iopub.status.busy":"2024-10-08T05:24:52.250948Z","iopub.execute_input":"2024-10-08T05:24:52.251364Z","iopub.status.idle":"2024-10-08T05:25:12.078991Z","shell.execute_reply.started":"2024-10-08T05:24:52.251325Z","shell.execute_reply":"2024-10-08T05:25:12.078128Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load and preprocess the dataset\ndef decode_image(image):\n    image = tf.image.decode_jpeg(image, channels=3)\n    image = (tf.cast(image, tf.float32) / 127.5) - 1\n    image = tf.reshape(image, [IMG_WIDTH, IMG_HEIGHT, 3])\n    return image\n\ndef read_tfrecord(example):\n    tfrecord_format = {\n        \"image\": tf.io.FixedLenFeature([], tf.string)\n    }\n    example = tf.io.parse_single_example(example, tfrecord_format)\n    image = decode_image(example['image'])\n    return image\n\ndef load_dataset(filenames):\n    dataset = tf.data.TFRecordDataset(filenames)\n    dataset = dataset.map(read_tfrecord, num_parallel_calls=AUTOTUNE)\n    return dataset\n\ndef prepare_dataset(dataset):\n    dataset = dataset.cache()\n    dataset = dataset.shuffle(BUFFER_SIZE)\n    dataset = dataset.batch(BATCH_SIZE)\n    dataset = dataset.prefetch(buffer_size=AUTOTUNE)\n    return dataset\n","metadata":{"execution":{"iopub.status.busy":"2024-10-08T05:25:24.477886Z","iopub.execute_input":"2024-10-08T05:25:24.478825Z","iopub.status.idle":"2024-10-08T05:25:24.486804Z","shell.execute_reply.started":"2024-10-08T05:25:24.478753Z","shell.execute_reply":"2024-10-08T05:25:24.485906Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load the datasets\nmonet_filenames = tf.io.gfile.glob('/kaggle/input/gan-getting-started/monet_tfrec/*.tfrec')\nphoto_filenames = tf.io.gfile.glob('/kaggle/input/gan-getting-started/photo_tfrec/*.tfrec')\n\nmonet_dataset = load_dataset(monet_filenames)\nphoto_dataset = load_dataset(photo_filenames)\n\nmonet_dataset = prepare_dataset(monet_dataset)\nphoto_dataset = prepare_dataset(photo_dataset)\n\n# Sample images for visualization\nsample_monet = next(iter(monet_dataset))\nsample_photo = next(iter(photo_dataset))\n","metadata":{"execution":{"iopub.status.busy":"2024-10-08T05:25:29.054734Z","iopub.execute_input":"2024-10-08T05:25:29.055369Z","iopub.status.idle":"2024-10-08T05:25:31.666920Z","shell.execute_reply.started":"2024-10-08T05:25:29.055329Z","shell.execute_reply":"2024-10-08T05:25:31.665827Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define the generators and discriminators\ndef instance_norm(epsilon=1e-5):\n    return tf.keras.layers.LayerNormalization(epsilon=epsilon, center=True, scale=True)\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(tf.keras.layers.Conv2D(filters, size, strides=2, padding='same',\n                                      kernel_initializer=initializer, use_bias=False))\n    if apply_instancenorm:\n        result.add(instance_norm())\n    result.add(tf.keras.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(tf.keras.layers.Conv2DTranspose(filters, size, strides=2,\n                                               padding='same',\n                                               kernel_initializer=initializer,\n                                               use_bias=False))\n    result.add(instance_norm())\n    if apply_dropout:\n        result.add(tf.keras.layers.Dropout(0.5))\n    result.add(tf.keras.layers.ReLU())\n    return result\n\ndef Generator():\n    inputs = tf.keras.layers.Input(shape=[IMG_WIDTH, IMG_HEIGHT, 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    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 = tf.keras.layers.Conv2DTranspose(3, 4,\n                                           strides=2,\n                                           padding='same',\n                                           kernel_initializer=initializer,\n                                           activation='tanh')\n    \n    x = inputs\n    \n    skips = []\n    for down in down_stack:\n        x = down(x)\n        skips.append(x)\n    \n    skips = reversed(skips[:-1])\n    \n    for up, skip in zip(up_stack, skips):\n        x = up(x)\n        x = tf.keras.layers.Concatenate()([x, skip])\n        \n    x = last(x)\n    \n    return tf.keras.Model(inputs=inputs, outputs=x)\n\ndef Discriminator():\n    initializer = tf.random_normal_initializer(0., 0.02)\n    \n    inp = tf.keras.layers.Input(shape=[IMG_WIDTH, IMG_HEIGHT, 3], name='input_image')\n    \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 = tf.keras.layers.ZeroPadding2D()(down3)\n    conv = tf.keras.layers.Conv2D(512, 4, strides=1,\n                                  kernel_initializer=initializer,\n                                  use_bias=False)(zero_pad1)\n    \n    norm1 = instance_norm()(conv)\n    leaky_relu = tf.keras.layers.LeakyReLU()(norm1)\n    \n    zero_pad2 = tf.keras.layers.ZeroPadding2D()(leaky_relu)\n    \n    last = tf.keras.layers.Conv2D(1, 4, strides=1,\n                                  kernel_initializer=initializer)(zero_pad2)\n    \n    return tf.keras.Model(inputs=inp, outputs=last)\n","metadata":{"execution":{"iopub.status.busy":"2024-10-08T05:25:41.837369Z","iopub.execute_input":"2024-10-08T05:25:41.838107Z","iopub.status.idle":"2024-10-08T05:25:41.860901Z","shell.execute_reply.started":"2024-10-08T05:25:41.838057Z","shell.execute_reply":"2024-10-08T05:25:41.859761Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Instantiate the models\ngenerator_g = Generator()\ngenerator_f = Generator()\n\ndiscriminator_x = Discriminator()\ndiscriminator_y = Discriminator()\n\n# Loss functions\nloss_obj = tf.keras.losses.BinaryCrossentropy(from_logits=True)\n","metadata":{"execution":{"iopub.status.busy":"2024-10-08T05:25:46.721867Z","iopub.execute_input":"2024-10-08T05:25:46.722302Z","iopub.status.idle":"2024-10-08T05:25:47.448744Z","shell.execute_reply.started":"2024-10-08T05:25:46.722265Z","shell.execute_reply":"2024-10-08T05:25:47.447931Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def discriminator_loss(real, generated):\n    real_loss = loss_obj(tf.ones_like(real), real)\n    generated_loss = 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 loss_obj(tf.ones_like(generated), generated)\n\ndef calc_cycle_loss(real_image, cycled_image):\n    loss1 = tf.reduce_mean(tf.abs(real_image - cycled_image))\n    return LAMBDA * loss1\n\ndef identity_loss(real_image, same_image):\n    loss = tf.reduce_mean(tf.abs(real_image - same_image))\n    return LAMBDA * 0.5 * loss\n","metadata":{"execution":{"iopub.status.busy":"2024-10-08T05:25:56.691584Z","iopub.execute_input":"2024-10-08T05:25:56.692358Z","iopub.status.idle":"2024-10-08T05:25:56.699870Z","shell.execute_reply.started":"2024-10-08T05:25:56.692313Z","shell.execute_reply":"2024-10-08T05:25:56.698848Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Optimizers\ngenerator_g_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\ngenerator_f_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n\ndiscriminator_x_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\ndiscriminator_y_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n\n# Checkpoints\ncheckpoint_path = \"./checkpoints/train\"\n\nckpt = tf.train.Checkpoint(generator_g=generator_g,\n                           generator_f=generator_f,\n                           discriminator_x=discriminator_x,\n                           discriminator_y=discriminator_y,\n                           generator_g_optimizer=generator_g_optimizer,\n                           generator_f_optimizer=generator_f_optimizer,\n                           discriminator_x_optimizer=discriminator_x_optimizer,\n                           discriminator_y_optimizer=discriminator_y_optimizer)\n\nckpt_manager = tf.train.CheckpointManager(ckpt, checkpoint_path, max_to_keep=5)\n\n# If a checkpoint exists, restore the latest checkpoint.\nif ckpt_manager.latest_checkpoint:\n    ckpt.restore(ckpt_manager.latest_checkpoint)\n    print ('Latest checkpoint restored!!')\n","metadata":{"execution":{"iopub.status.busy":"2024-10-08T05:26:00.976477Z","iopub.execute_input":"2024-10-08T05:26:00.976866Z","iopub.status.idle":"2024-10-08T05:26:00.997438Z","shell.execute_reply.started":"2024-10-08T05:26:00.976828Z","shell.execute_reply":"2024-10-08T05:26:00.996427Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Training\nEPOCHS = 3\n\ndef generate_images(model, test_input):\n    prediction = model(test_input)\n        \n    plt.figure(figsize=(12, 12))\n\n    display_list = [test_input[0], prediction[0]]\n    title = ['Input Image', 'Predicted Image']\n\n    for i in range(2):\n        plt.subplot(1, 2, i+1)\n        plt.title(title[i])\n        # getting the pixel values between [0, 1] to plot it.\n        plt.imshow(display_list[i] * 0.5 + 0.5)\n        plt.axis('off')\n    plt.show()\n\n@tf.function\ndef train_step(real_x, real_y):\n    # persistent is set to True because the tape is used more than\n    # once to calculate the gradients.\n    with tf.GradientTape(persistent=True) as tape:\n        # Generator G translates X -> Y\n        # Generator F translates Y -> X.\n        \n        fake_y = generator_g(real_x, training=True)\n        cycled_x = generator_f(fake_y, training=True)\n\n        fake_x = generator_f(real_y, training=True)\n        cycled_y = generator_g(fake_x, training=True)\n\n        # same_x and same_y are used for identity loss.\n        same_x = generator_f(real_x, training=True)\n        same_y = generator_g(real_y, training=True)\n\n        disc_real_x = discriminator_x(real_x, training=True)\n        disc_real_y = discriminator_y(real_y, training=True)\n\n        disc_fake_x = discriminator_x(fake_x, training=True)\n        disc_fake_y = discriminator_y(fake_y, training=True)\n\n        # calculate the loss\n        gen_g_loss = generator_loss(disc_fake_y)\n        gen_f_loss = generator_loss(disc_fake_x)\n        \n        total_cycle_loss = calc_cycle_loss(real_x, cycled_x) + calc_cycle_loss(real_y, cycled_y)\n        \n        # Total generator loss = adversarial loss + cycle loss\n        total_gen_g_loss = gen_g_loss + total_cycle_loss + identity_loss(real_y, same_y)\n        total_gen_f_loss = gen_f_loss + total_cycle_loss + identity_loss(real_x, same_x)\n\n        disc_x_loss = discriminator_loss(disc_real_x, disc_fake_x)\n        disc_y_loss = discriminator_loss(disc_real_y, disc_fake_y)\n    \n    # Calculate the gradients for generator and discriminator\n    generator_g_gradients = tape.gradient(total_gen_g_loss, \n                                          generator_g.trainable_variables)\n    generator_f_gradients = tape.gradient(total_gen_f_loss, \n                                          generator_f.trainable_variables)\n    \n    discriminator_x_gradients = tape.gradient(disc_x_loss, \n                                              discriminator_x.trainable_variables)\n    discriminator_y_gradients = tape.gradient(disc_y_loss, \n                                              discriminator_y.trainable_variables)\n    \n    # Apply the gradients to the optimizer\n    generator_g_optimizer.apply_gradients(zip(generator_g_gradients, \n                                              generator_g.trainable_variables))\n\n    generator_f_optimizer.apply_gradients(zip(generator_f_gradients, \n                                              generator_f.trainable_variables))\n    \n    discriminator_x_optimizer.apply_gradients(zip(discriminator_x_gradients,\n                                                  discriminator_x.trainable_variables))\n    \n    discriminator_y_optimizer.apply_gradients(zip(discriminator_y_gradients,\n                                                  discriminator_y.trainable_variables))\n\nfor epoch in range(EPOCHS):\n    start = time.time()\n\n    n = 0\n    for image_x, image_y in tf.data.Dataset.zip((monet_dataset, photo_dataset)):\n        train_step(image_x, image_y)\n        if n % 10 == 0:\n            print('.', end='')\n        n += 1\n\n    clear_output(wait=True)\n    # Using a consistent image (sample_photo) so that the progress of the model\n    # is clearly visible.\n    generate_images(generator_g, sample_photo)\n\n    if (epoch + 1) % 5 == 0:\n        ckpt_save_path = ckpt_manager.save()\n        print ('Saving checkpoint for epoch {} at {}'.format(epoch+1,\n                                                             ckpt_save_path))\n\n    print ('Time taken for epoch {} is {} sec\\n'.format(epoch + 1,\n                                                        time.time()-start))","metadata":{"execution":{"iopub.status.busy":"2024-10-08T05:26:05.750445Z","iopub.execute_input":"2024-10-08T05:26:05.751185Z","iopub.status.idle":"2024-10-08T05:30:29.893135Z","shell.execute_reply.started":"2024-10-08T05:26:05.751125Z","shell.execute_reply":"2024-10-08T05:30:29.892201Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from PIL import Image\nimport shutil\n# Function to generate and save the image after applying the model\ndef generate_and_save_image(model, image_tensor, output_path, file_name):\n    prediction = model(image_tensor)\n    plt.imshow(prediction[0] * 0.5 + 0.5)  # Rescale pixel values\n    plt.axis('off')\n    plt.savefig(os.path.join(output_path, file_name), bbox_inches='tight', pad_inches=0)\n    plt.close()\n\n# Directories\ninput_dir = \"/kaggle/input/gan-getting-started/photo_jpg\"\noutput_dir = \"/kaggle/working/images\"\nos.makedirs(output_dir, exist_ok=True)\n\n# Iterate through all images in the input folder, apply style transfer, and save the output\nfor i, file_name in enumerate(os.listdir(input_dir)):\n    if file_name.endswith('.jpg'):\n        img = Image.open(os.path.join(input_dir, file_name))\n        img_tensor = tf.convert_to_tensor(img,dtype=tf.float32) / 255.0  # Normalize image\n        img_tensor = tf.expand_dims(img_tensor, 0)  # Add batch dimension\n        \n        generate_and_save_image(generator_g, img_tensor, output_dir, f'image_{i+1}.jpg')\n        \nshutil.make_archive(\"/kaggle/working/images\", 'zip', \"/kaggle/images\")","metadata":{"execution":{"iopub.status.busy":"2024-10-08T05:43:16.181292Z","iopub.execute_input":"2024-10-08T05:43:16.181855Z","iopub.status.idle":"2024-10-08T06:06:53.454384Z","shell.execute_reply.started":"2024-10-08T05:43:16.181808Z","shell.execute_reply":"2024-10-08T06:06:53.453367Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n\n\n\n\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]}]}