{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceType":"competition","sourceId":21755,"databundleVersionId":1475600}],"dockerImageVersionId":31329,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:42:02.588482Z","iopub.execute_input":"2026-04-20T04:42:02.588917Z","iopub.status.idle":"2026-04-20T04:42:21.531139Z","shell.execute_reply.started":"2026-04-20T04:42:02.588887Z","shell.execute_reply":"2026-04-20T04:42:21.530313Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"path = \"/kaggle/input/competitions/gan-getting-started/\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:42:21.532426Z","iopub.execute_input":"2026-04-20T04:42:21.532873Z","iopub.status.idle":"2026-04-20T04:42:21.536255Z","shell.execute_reply.started":"2026-04-20T04:42:21.532847Z","shell.execute_reply":"2026-04-20T04:42:21.535618Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\n\ndef count_files(directory):\n    return len([f for f in os.listdir(directory) if os.path.isfile(os.path.join(directory, f))])\n\nmonet_jpg_path = os.path.join(path, 'monet_jpg')\nphoto_jpg_path = os.path.join(path, 'photo_jpg')\n\nprint(f\"Number of Monet JPEG images: {count_files(monet_jpg_path)}\")\nprint(f\"Number of Photo JPEG images: {count_files(photo_jpg_path)}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:42:21.537089Z","iopub.execute_input":"2026-04-20T04:42:21.537481Z","iopub.status.idle":"2026-04-20T04:42:29.334766Z","shell.execute_reply.started":"2026-04-20T04:42:21.537436Z","shell.execute_reply":"2026-04-20T04:42:29.334093Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nfrom PIL import Image\n\ndef display_samples(directory, num_samples=3, title=\"Samples\"):\n    files = os.listdir(directory)[:num_samples]\n    plt.figure(figsize=(15, 5))\n    for i, file in enumerate(files):\n        img_path = os.path.join(directory, file)\n        img = Image.open(img_path)\n        plt.subplot(1, num_samples, i + 1)\n        plt.imshow(img)\n        plt.axis('off')\n    plt.suptitle(title)\n    plt.show()\n\ndisplay_samples(monet_jpg_path, title=\"Monet Painting Samples\")\ndisplay_samples(photo_jpg_path, title=\"Photo Samples\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:42:29.336173Z","iopub.execute_input":"2026-04-20T04:42:29.336380Z","iopub.status.idle":"2026-04-20T04:42:30.083976Z","shell.execute_reply.started":"2026-04-20T04:42:29.336361Z","shell.execute_reply":"2026-04-20T04:42:30.083173Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\nimport glob\n\n# Define the paths for TFRecord files\nMONET_FILENAMES = tf.io.gfile.glob(str(path + '/monet_tfrec/*.tfrec'))\nPHOTO_FILENAMES = tf.io.gfile.glob(str(path + '/photo_tfrec/*.tfrec'))\n\nprint(f\"Monet TFRecord files: {len(MONET_FILENAMES)}\")\nprint(f\"Photo TFRecord files: {len(PHOTO_FILENAMES)}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:42:30.085164Z","iopub.execute_input":"2026-04-20T04:42:30.085418Z","iopub.status.idle":"2026-04-20T04:43:09.983709Z","shell.execute_reply.started":"2026-04-20T04:42:30.085394Z","shell.execute_reply":"2026-04-20T04:43:09.982964Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = [256, 256]\n\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, [*IMAGE_SIZE, 3])\n    return image\n\ndef read_tfrecord(example):\n    tfrecord_format = {\n        \"image_name\": tf.io.FixedLenFeature([], tf.string),\n        \"image\": tf.io.FixedLenFeature([], tf.string),\n        \"target\": 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, labeled=True, ordered=False):\n    dataset = tf.data.TFRecordDataset(filenames)\n    dataset = dataset.map(read_tfrecord, num_parallel_calls=tf.data.AUTOTUNE)\n    return dataset","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:43:09.984646Z","iopub.execute_input":"2026-04-20T04:43:09.985209Z","iopub.status.idle":"2026-04-20T04:43:09.991217Z","shell.execute_reply.started":"2026-04-20T04:43:09.985174Z","shell.execute_reply":"2026-04-20T04:43:09.990538Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"OUTPUT_CHANNELS = 3\n\ndef downsample(filters, size, apply_instancenorm=True):\n    initializer = tf.random_normal_initializer(0., 0.02)\n\n    result = tf.keras.Sequential()\n    result.add(\n        tf.keras.layers.Conv2D(filters, size, strides=2, padding='same',\n                               kernel_initializer=initializer, use_bias=False))\n\n    if apply_instancenorm:\n        result.add(tf.keras.layers.GroupNormalization(groups=-1))\n\n    result.add(tf.keras.layers.LeakyReLU())\n\n    return result\n\ndef upsample(filters, size, apply_dropout=False):\n    initializer = tf.random_normal_initializer(0., 0.02)\n\n    result = tf.keras.Sequential()\n    result.add(\n        tf.keras.layers.Conv2DTranspose(filters, size, strides=2,\n                                        padding='same',\n                                        kernel_initializer=initializer,\n                                        use_bias=False))\n\n    result.add(tf.keras.layers.GroupNormalization(groups=-1))\n\n    if apply_dropout:\n        result.add(tf.keras.layers.Dropout(0.5))\n\n    result.add(tf.keras.layers.ReLU())\n\n    return result","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:43:09.992200Z","iopub.execute_input":"2026-04-20T04:43:09.992456Z","iopub.status.idle":"2026-04-20T04:43:10.034580Z","shell.execute_reply.started":"2026-04-20T04:43:09.992421Z","shell.execute_reply":"2026-04-20T04:43:10.033878Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"monet_ds = load_dataset(MONET_FILENAMES, labeled=True).batch(1)\nphoto_ds = load_dataset(PHOTO_FILENAMES, labeled=True).batch(1)\n\nexample_monet = next(iter(monet_ds))\nexample_photo = next(iter(photo_ds))\n\nprint(f\"Monet batch shape: {example_monet.shape}\")\nprint(f\"Photo batch shape: {example_photo.shape}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:43:10.035473Z","iopub.execute_input":"2026-04-20T04:43:10.036213Z","iopub.status.idle":"2026-04-20T04:43:12.803443Z","shell.execute_reply.started":"2026-04-20T04:43:10.036186Z","shell.execute_reply":"2026-04-20T04:43:12.802768Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def Generator():\n    inputs = tf.keras.layers.Input(shape=[256, 256, 3])\n\n    down_stack = [\n        downsample(64, 4, apply_instancenorm=False), # (batch_size, 128, 128, 64)\n        downsample(128, 4), # (batch_size, 64, 64, 128)\n        downsample(256, 4), # (batch_size, 32, 32, 256)\n        downsample(512, 4), # (batch_size, 16, 16, 512)\n        downsample(512, 4), # (batch_size, 8, 8, 512)\n        downsample(512, 4), # (batch_size, 4, 4, 512)\n        downsample(512, 4), # (batch_size, 2, 2, 512)\n        downsample(512, 4), # (batch_size, 1, 1, 512)\n    ]\n\n    up_stack = [\n        upsample(512, 4, apply_dropout=True), # (batch_size, 2, 2, 1024)\n        upsample(512, 4, apply_dropout=True), # (batch_size, 4, 4, 1024)\n        upsample(512, 4, apply_dropout=True), # (batch_size, 8, 8, 1024)\n        upsample(512, 4), # (batch_size, 16, 16, 1024)\n        upsample(256, 4), # (batch_size, 32, 32, 512)\n        upsample(128, 4), # (batch_size, 64, 64, 256)\n        upsample(64, 4), # (batch_size, 128, 128, 128)\n    ]\n\n    initializer = tf.random_normal_initializer(0., 0.02)\n    last = tf.keras.layers.Conv2DTranspose(OUTPUT_CHANNELS, 4,\n                                         strides=2,\n                                         padding='same',\n                                         kernel_initializer=initializer,\n                                         activation='tanh') # (batch_size, 256, 256, 3)\n\n    x = inputs\n\n    # Downsampling through the model\n    skips = []\n    for down in down_stack:\n        x = down(x)\n        skips.append(x)\n\n    skips = reversed(skips[:-1])\n\n    # Upsampling and establishing the skip connections\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\ngenerator = Generator()\ngenerator.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:43:12.804646Z","iopub.execute_input":"2026-04-20T04:43:12.804942Z","iopub.status.idle":"2026-04-20T04:43:13.085253Z","shell.execute_reply.started":"2026-04-20T04:43:12.804918Z","shell.execute_reply":"2026-04-20T04:43:13.084660Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def Discriminator():\n    initializer = tf.random_normal_initializer(0., 0.02)\n\n    inp = tf.keras.layers.Input(shape=[256, 256, 3], name='input_image')\n\n    x = inp\n\n    down1 = downsample(64, 4, False)(x) # (batch_size, 128, 128, 64)\n    down2 = downsample(128, 4)(down1) # (batch_size, 64, 64, 128)\n    down3 = downsample(256, 4)(down2) # (batch_size, 32, 32, 256)\n\n    zero_pad1 = tf.keras.layers.ZeroPadding2D()(down3) # (batch_size, 34, 34, 256)\n    conv = tf.keras.layers.Conv2D(512, 4, strides=1,\n                                  kernel_initializer=initializer,\n                                  use_bias=False)(zero_pad1) # (batch_size, 31, 31, 512)\n\n    norm1 = tf.keras.layers.GroupNormalization(groups=-1)(conv)\n\n    leaky_rely = tf.keras.layers.LeakyReLU()(norm1)\n\n    zero_pad2 = tf.keras.layers.ZeroPadding2D()(leaky_rely) # (batch_size, 33, 33, 512)\n\n    last = tf.keras.layers.Conv2D(1, 4, strides=1,\n                                  kernel_initializer=initializer)(zero_pad2) # (batch_size, 30, 30, 1)\n\n    return tf.keras.Model(inputs=inp, outputs=last)\n\ndiscriminator = Discriminator()\ndiscriminator.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:43:13.087165Z","iopub.execute_input":"2026-04-20T04:43:13.087445Z","iopub.status.idle":"2026-04-20T04:43:13.159448Z","shell.execute_reply.started":"2026-04-20T04:43:13.087420Z","shell.execute_reply":"2026-04-20T04:43:13.158929Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class CycleGan(tf.keras.Model):\n  def __init__(self, monet_generator, photo_generator, monet_discriminator, photo_discriminator):\n    super().__init__()\n    self.monet_generator = monet_generator\n    self.photo_generator = photo_generator\n    self.monet_discriminator = monet_discriminator\n    self.photo_discriminator = photo_discriminator\n\n  def compile(self,\n              monet_generator_optimizer,\n              photo_generator_optimizer,\n              monet_discriminator_optimizer,\n              photo_discriminator_optimizer,\n              generator_loss_fn,\n              discriminator_loss_fn,\n              cycle_loss_fn,\n              identity_loss_fn):\n    super().compile()\n    self.monet_generator_optimizer = monet_generator_optimizer\n    self.photo_generator_optimizer = photo_generator_optimizer\n    self.monet_discriminator_optimizer = monet_discriminator_optimizer\n    self.photo_discriminator_optimizer = photo_discriminator_optimizer\n    self.generator_loss_fn = generator_loss_fn\n    self.discriminator_loss_fn = discriminator_loss_fn\n    self.cycle_loss_fn = cycle_loss_fn\n    self.identity_loss_fn = identity_loss_fn\n\n  def train_step(self, batch_data):\n    real_monet, real_photo = batch_data\n\n    with tf.GradientTape(persistent=True) as tape:\n      # generate monet from photo\n      fake_monet = self.monet_generator(real_photo, training=True)\n      # generate photo from monet\n      fake_photo = self.photo_generator(real_monet, training=True)\n\n      # cycle gan\n      cycled_photo = self.photo_generator(fake_monet, training=True)\n      cycled_monet = self.monet_generator(fake_photo, training=True)\n\n      # identity mapping\n      same_monet = self.monet_generator(real_monet, training=True)\n      same_photo = self.photo_generator(real_photo, training=True)\n\n      # discriminate\n      monet_disc_real = self.monet_discriminator(real_monet, training=True)\n      monet_disc_fake = self.monet_discriminator(fake_monet, training=True)\n\n      photo_disc_real = self.photo_discriminator(real_photo, training=True)\n      photo_disc_fake = self.photo_discriminator(fake_photo, training=True)\n\n      # evaluate loss\n      monet_gen_loss = self.generator_loss_fn(monet_disc_fake)\n      photo_gen_loss = self.generator_loss_fn(photo_disc_fake)\n\n      total_monet_gen_loss = monet_gen_loss + self.cycle_loss_fn(real_monet, cycled_monet) + self.identity_loss_fn(real_monet, same_monet)\n      total_photo_gen_loss = photo_gen_loss + self.cycle_loss_fn(real_photo, cycled_photo) + self.identity_loss_fn(real_photo, same_photo)\n\n      monet_disc_loss = self.discriminator_loss_fn(monet_disc_real, monet_disc_fake)\n      photo_disc_loss = self.discriminator_loss_fn(photo_disc_real, photo_disc_fake)\n\n    # Calculate the gradients for generator and discriminator\n    monet_generator_gradients = tape.gradient(total_monet_gen_loss, self.monet_generator.trainable_variables)\n    photo_generator_gradients = tape.gradient(total_photo_gen_loss, self.photo_generator.trainable_variables)\n\n    monet_discriminator_gradients = tape.gradient(monet_disc_loss, self.monet_discriminator.trainable_variables)\n    photo_discriminator_gradients = tape.gradient(photo_disc_loss, self.photo_discriminator.trainable_variables)\n\n    # Apply the gradients to the optimizers\n    self.monet_generator_optimizer.apply_gradients(zip(monet_generator_gradients, self.monet_generator.trainable_variables))\n    self.photo_generator_optimizer.apply_gradients(zip(photo_generator_gradients, self.photo_generator.trainable_variables))\n\n    self.monet_discriminator_optimizer.apply_gradients(zip(monet_discriminator_gradients, self.monet_discriminator.trainable_variables))\n    self.photo_discriminator_optimizer.apply_gradients(zip(photo_discriminator_gradients, self.photo_discriminator.trainable_variables))\n\n    return {\n        \"monet_generator_loss\": total_monet_gen_loss,\n        \"photo_generator_loss\": total_photo_gen_loss,\n        \"monet_discriminator_loss\": monet_disc_loss,\n        \"photo_discriminator_loss\": photo_disc_loss\n    }","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:43:13.160287Z","iopub.execute_input":"2026-04-20T04:43:13.160569Z","iopub.status.idle":"2026-04-20T04:43:13.171178Z","shell.execute_reply.started":"2026-04-20T04:43:13.160547Z","shell.execute_reply":"2026-04-20T04:43:13.170309Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Define loss functions\n\nLAMBDA = 10\n\nloss_obj = tf.keras.losses.BinaryCrossentropy(from_logits=True)\n\ndef discriminator_loss(real, fake):\n  real_loss = loss_obj(tf.ones_like(real), real)\n  fake_loss = loss_obj(tf.zeros_like(fake), fake)\n  total_disc_loss = real_loss + fake_loss\n  return total_disc_loss * 0.5\n\ndef generator_loss(fake):\n  return loss_obj(tf.ones_like(fake), fake)\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\n\n# Define optimizers\n\nmonet_generator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\nphoto_generator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n\nmonet_discriminator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\nphoto_discriminator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n\n# Instantiate the Generators and Discriminators\nmonet_generator = Generator()\nphoto_generator = Generator()\n\nmonet_discriminator = Discriminator()\nphoto_discriminator = Discriminator()\n\n# Instantiate the CycleGAN model\ncycle_gan_model = CycleGan(\n    monet_generator,\n    photo_generator,\n    monet_discriminator,\n    photo_discriminator\n)\n\n# Compile the model\ncycle_gan_model.compile(\n    monet_generator_optimizer=monet_generator_optimizer,\n    photo_generator_optimizer=photo_generator_optimizer,\n    monet_discriminator_optimizer=monet_discriminator_optimizer,\n    photo_discriminator_optimizer=photo_discriminator_optimizer,\n    generator_loss_fn=generator_loss,\n    discriminator_loss_fn=discriminator_loss,\n    cycle_loss_fn=calc_cycle_loss,\n    identity_loss_fn=identity_loss\n)\n\nprint(\"CycleGAN model defined, compiled and ready for training!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:43:13.172100Z","iopub.execute_input":"2026-04-20T04:43:13.172534Z","iopub.status.idle":"2026-04-20T04:43:13.648907Z","shell.execute_reply.started":"2026-04-20T04:43:13.172501Z","shell.execute_reply":"2026-04-20T04:43:13.648259Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"EPOCHS = 20\n\n# Configure the datasets for training\n# Repeat the datasets indefinitely and batch them\nmonet_dataset = load_dataset(MONET_FILENAMES).shuffle(buffer_size=1024).batch(1).repeat()\nphoto_dataset = load_dataset(PHOTO_FILENAMES).shuffle(buffer_size=1024).batch(1).repeat()\n\n# Train the model\nhistory = cycle_gan_model.fit(\n    tf.data.Dataset.zip((monet_dataset, photo_dataset)),\n    epochs=EPOCHS,\n    steps_per_epoch=max(len(MONET_FILENAMES) * 60, len(PHOTO_FILENAMES) * 60) # Adjust steps_per_epoch based on dataset size\n)\n\nprint(\"Training complete!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T04:43:13.649911Z","iopub.execute_input":"2026-04-20T04:43:13.650454Z","iopub.status.idle":"2026-04-20T06:13:12.917414Z","shell.execute_reply.started":"2026-04-20T04:43:13.650428Z","shell.execute_reply":"2026-04-20T06:13:12.916615Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef generate_images(model, test_input, title=\"Generated Images\"):\n  prediction = model(test_input)\n\n  plt.figure(figsize=(15, 15))\n\n  display_list = [test_input[0], prediction[0]]\n  title_list = ['Input Image', 'Generated Image']\n\n  for i in range(2):\n    plt.subplot(1, 2, i+1)\n    plt.title(title_list[i])\n    # Getting the pixel values in the [0, 1] range to plot.\n    plt.imshow(display_list[i] * 0.5 + 0.5)\n    plt.axis('off')\n  plt.suptitle(title, fontsize=16)\n  plt.show()\n\n# Take a few example photos from the dataset\nfor i, example_photo in enumerate(photo_ds.take(5)):\n  generate_images(monet_generator, example_photo, title=f'Example {i+1}: Photo to Monet')\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T06:13:12.918615Z","iopub.execute_input":"2026-04-20T06:13:12.918998Z","iopub.status.idle":"2026-04-20T06:13:17.319114Z","shell.execute_reply.started":"2026-04-20T06:13:12.918974Z","shell.execute_reply":"2026-04-20T06:13:17.318287Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import PIL\nimport numpy as np\n\n# Create a directory for the output images\noutput_dir = 'images'\nos.makedirs(output_dir, exist_ok=True)\n\n# Iterate through the photo dataset and generate Monet-style images\ni = 0\nfor img in photo_ds:\n    prediction = monet_generator(img, training=False)[0].numpy()\n    # Rescale image from [-1, 1] to [0, 255] and convert to uint8\n    prediction = (prediction * 127.5 + 127.5).astype(np.uint8)\n    # Create a PIL Image object\n    img_pil = PIL.Image.fromarray(prediction)\n    # Save the image\n    img_pil.save(os.path.join(output_dir, f'{i}.jpg'))\n    i += 1\n\nprint(f\"Generated {i} images.\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-04-20T06:13:17.320233Z","iopub.execute_input":"2026-04-20T06:13:17.320452Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Create the submission zip file\nimport shutil\nshutil.make_archive('images', 'zip', output_dir)\n\nprint(\"Submission file 'images.zip' created successfully!\")","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}