{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# CycleGAN to generate Monet-style images","metadata":{}},{"cell_type":"markdown","source":"This notebook is inspired by Amy Jang's tutorial notebook.","metadata":{}},{"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","execution":{"iopub.status.busy":"2021-11-07T13:08:10.439486Z","iopub.execute_input":"2021-11-07T13:08:10.439863Z","iopub.status.idle":"2021-11-07T13:08:14.840508Z","shell.execute_reply.started":"2021-11-07T13:08:10.439757Z","shell.execute_reply":"2021-11-07T13:08:14.839527Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport math\nimport random\nimport matplotlib.pyplot as plt\nimport cv2\nimport tensorflow as tf\nfrom   tensorflow import keras\nfrom   tensorflow.keras import layers\nimport tensorflow_addons as tfa\nimport tensorflow_datasets as tfds\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport tensorflow.keras.backend as K\nimport os, random, json, PIL, shutil, re, imageio, glob\nfrom tensorflow.keras import Model, losses, optimizers\nfrom tensorflow.keras.callbacks import Callback\nfrom kaggle_datasets import KaggleDatasets","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","execution":{"iopub.status.busy":"2021-11-07T13:08:29.652551Z","iopub.execute_input":"2021-11-07T13:08:29.652835Z","iopub.status.idle":"2021-11-07T13:08:36.538789Z","shell.execute_reply.started":"2021-11-07T13:08:29.652807Z","shell.execute_reply":"2021-11-07T13:08:36.538014Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Configuring TPU\n\ntry:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    print(f'Running on TPU {tpu.master()}')\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy()\n\n\nREPLICAS = strategy.num_replicas_in_sync\nAUTO = tf.data.experimental.AUTOTUNE\nprint(f'REPLICAS: {REPLICAS}')","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:08:40.844313Z","iopub.execute_input":"2021-11-07T13:08:40.844960Z","iopub.status.idle":"2021-11-07T13:08:46.895704Z","shell.execute_reply.started":"2021-11-07T13:08:40.844923Z","shell.execute_reply":"2021-11-07T13:08:46.894832Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"BASE_PATH = '../input/gan-getting-started/'\nMONET_PATH = os.path.join(BASE_PATH, 'monet_jpg')\nPHOTO_PATH = os.path.join(BASE_PATH, 'photo_jpg')","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:08:52.266216Z","iopub.execute_input":"2021-11-07T13:08:52.266483Z","iopub.status.idle":"2021-11-07T13:08:52.270986Z","shell.execute_reply.started":"2021-11-07T13:08:52.266456Z","shell.execute_reply":"2021-11-07T13:08:52.270128Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def show_folder_info(path):\n    d_image_sizes = {}\n    for image_name in os.listdir(path):\n        image = cv2.imread(os.path.join(path, image_name))\n        d_image_sizes[image.shape] = d_image_sizes.get(image.shape, 0) + 1\n        \n    for size, count in d_image_sizes.items():\n        print(f'shape: {size}\\tcount: {count}')\n\n\nprint('Monet images:')\nshow_folder_info(MONET_PATH)\n\nprint('Photo images:')\nshow_folder_info(PHOTO_PATH)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:09:04.932903Z","iopub.execute_input":"2021-11-07T13:09:04.933231Z","iopub.status.idle":"2021-11-07T13:10:03.485589Z","shell.execute_reply.started":"2021-11-07T13:09:04.933192Z","shell.execute_reply":"2021-11-07T13:10:03.484837Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" # Visualization","metadata":{}},{"cell_type":"markdown","source":"## (1) Batch visualization","metadata":{}},{"cell_type":"code","source":"def batch_visualization(path, n_images, is_random=True, figsize=(16, 16)):\n    plt.figure(figsize=figsize)\n    \n    w = int(n_images ** .5)\n    h = math.ceil(n_images / w)\n    \n    all_names = os.listdir(path)\n    \n    image_names = all_names[:n_images]\n    if is_random:\n        image_names = random.sample(all_names, n_images)\n    \n    for ind, image_name in enumerate(image_names):\n        img = cv2.imread(os.path.join(path, image_name))\n        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) \n        plt.subplot(h, w, ind + 1)\n        plt.imshow(img)\n        plt.axis('off')\n    \n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:10:22.593440Z","iopub.execute_input":"2021-11-07T13:10:22.593709Z","iopub.status.idle":"2021-11-07T13:10:22.601750Z","shell.execute_reply.started":"2021-11-07T13:10:22.593682Z","shell.execute_reply":"2021-11-07T13:10:22.601112Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"batch_visualization(MONET_PATH, 12, is_random=True, figsize=(23, 23))","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:10:26.758652Z","iopub.execute_input":"2021-11-07T13:10:26.759420Z","iopub.status.idle":"2021-11-07T13:10:28.276915Z","shell.execute_reply.started":"2021-11-07T13:10:26.759383Z","shell.execute_reply":"2021-11-07T13:10:28.276024Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"batch_visualization(PHOTO_PATH, 12, is_random=True, figsize=(23, 23))","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:10:34.331121Z","iopub.execute_input":"2021-11-07T13:10:34.331406Z","iopub.status.idle":"2021-11-07T13:10:35.762914Z","shell.execute_reply.started":"2021-11-07T13:10:34.331376Z","shell.execute_reply":"2021-11-07T13:10:35.762125Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## (2) Colour histograms","metadata":{}},{"cell_type":"code","source":"# Plotting colour histograms for Monet paintings\ndef color_hist_visualization(image_path, figsize=(16, 4)):\n    plt.figure(figsize=figsize)\n    colors = ['red', 'green', 'blue']\n    \n    img = cv2.imread(image_path)\n    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) \n    plt.subplot(1, 4, 1)\n    plt.imshow(img)\n    plt.axis('off')\n    \n    for i in range(len(colors)):\n        plt.subplot(1, 4, i + 2)\n        plt.hist(\n            img[:, :, i].reshape(-1),\n            bins=25,\n            alpha=0.5,\n            color=colors[i],\n            density=True\n        )\n        plt.xlim(0, 255)\n        plt.xticks([])\n        plt.yticks([])\n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:10:40.946987Z","iopub.execute_input":"2021-11-07T13:10:40.947510Z","iopub.status.idle":"2021-11-07T13:10:40.955812Z","shell.execute_reply.started":"2021-11-07T13:10:40.947476Z","shell.execute_reply":"2021-11-07T13:10:40.954640Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_path = '../input/gan-getting-started/monet_jpg/05b493ff42.jpg'\ncolor_hist_visualization(img_path)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:10:46.096519Z","iopub.execute_input":"2021-11-07T13:10:46.096829Z","iopub.status.idle":"2021-11-07T13:10:46.505280Z","shell.execute_reply.started":"2021-11-07T13:10:46.096797Z","shell.execute_reply":"2021-11-07T13:10:46.504466Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_path = '../input/gan-getting-started/monet_jpg/052a77c020.jpg'\ncolor_hist_visualization(img_path)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:10:49.552537Z","iopub.execute_input":"2021-11-07T13:10:49.553413Z","iopub.status.idle":"2021-11-07T13:10:50.191576Z","shell.execute_reply.started":"2021-11-07T13:10:49.553374Z","shell.execute_reply":"2021-11-07T13:10:50.190667Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_path = '../input/gan-getting-started/monet_jpg/09b76b6471.jpg'\ncolor_hist_visualization(img_path)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:10:53.184644Z","iopub.execute_input":"2021-11-07T13:10:53.185335Z","iopub.status.idle":"2021-11-07T13:10:53.588338Z","shell.execute_reply.started":"2021-11-07T13:10:53.185293Z","shell.execute_reply":"2021-11-07T13:10:53.587713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## (3) Individual channels visualization","metadata":{}},{"cell_type":"code","source":"# Individual channels visualization \ndef channels_visualization(image_path, figsize=(16, 4)):\n    plt.figure(figsize=figsize)\n    \n    img = cv2.imread(image_path)\n    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) \n    plt.subplot(1, 4, 1)\n    plt.imshow(img)\n    plt.axis('off')\n    \n    for i in range(3):\n        plt.subplot(1, 4, i + 2)\n        tmp_img = np.full_like(img, 0)\n        tmp_img[:, :, i] = img[:, :, i]\n        plt.imshow(tmp_img)\n        plt.xlim(0, 255)\n        plt.xticks([])\n        plt.yticks([])\n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:10:57.891684Z","iopub.execute_input":"2021-11-07T13:10:57.892180Z","iopub.status.idle":"2021-11-07T13:10:57.899356Z","shell.execute_reply.started":"2021-11-07T13:10:57.892133Z","shell.execute_reply":"2021-11-07T13:10:57.898403Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_path = '../input/gan-getting-started/monet_jpg/0bd913dbc7.jpg'\ncolor_hist_visualization(img_path)\nchannels_visualization(img_path)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:11:02.679957Z","iopub.execute_input":"2021-11-07T13:11:02.680252Z","iopub.status.idle":"2021-11-07T13:11:03.425837Z","shell.execute_reply.started":"2021-11-07T13:11:02.680221Z","shell.execute_reply":"2021-11-07T13:11:03.424822Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## (4) Greyscale visualization","metadata":{}},{"cell_type":"code","source":"# Grayscale visualization\ndef grayscale_visualization(image_path, figsize=(8, 4)):\n    plt.figure(figsize=figsize)\n    \n    img = cv2.imread(image_path)\n    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) \n    plt.subplot(1, 2, 1)\n    plt.imshow(img)\n    plt.axis('off')\n    \n    plt.subplot(1, 2, 2)\n    tmp_img = np.full_like(img, 0)\n    for i in range(3):\n        tmp_img[:, :, i] = img.mean(axis=-1)\n    plt.imshow(tmp_img)\n    plt.axis('off')\n    \n    \n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:11:08.192715Z","iopub.execute_input":"2021-11-07T13:11:08.192994Z","iopub.status.idle":"2021-11-07T13:11:08.200004Z","shell.execute_reply.started":"2021-11-07T13:11:08.192967Z","shell.execute_reply":"2021-11-07T13:11:08.199236Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_path = '../input/gan-getting-started/monet_jpg/990ed28f62.jpg'\ngrayscale_visualization(img_path)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:11:13.509390Z","iopub.execute_input":"2021-11-07T13:11:13.510142Z","iopub.status.idle":"2021-11-07T13:11:13.753919Z","shell.execute_reply.started":"2021-11-07T13:11:13.510104Z","shell.execute_reply":"2021-11-07T13:11:13.753304Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load the datasets","metadata":{}},{"cell_type":"code","source":"GCS_PATH = KaggleDatasets().get_gcs_path()","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:11:16.960390Z","iopub.execute_input":"2021-11-07T13:11:16.961349Z","iopub.status.idle":"2021-11-07T13:11:17.616271Z","shell.execute_reply.started":"2021-11-07T13:11:16.961278Z","shell.execute_reply":"2021-11-07T13:11:17.615330Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Load the TFRecord files","metadata":{}},{"cell_type":"code","source":"# Get the Google Cloud Storage path URI (GCS path) for Kaggle Datasets\nGCS_PATH = KaggleDatasets().get_gcs_path('gan-getting-started')\n\nGCS_PATH","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:11:21.181875Z","iopub.execute_input":"2021-11-07T13:11:21.182166Z","iopub.status.idle":"2021-11-07T13:11:21.583640Z","shell.execute_reply.started":"2021-11-07T13:11:21.182134Z","shell.execute_reply":"2021-11-07T13:11:21.582842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Obtain two lists of files that match the given patterns specified in str()\ndef count_data_items(filenames):\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n    return np.sum(n)\n\nMONET_FILENAMES = tf.io.gfile.glob(str(GCS_PATH + '/monet_tfrec/*.tfrec'))\nPHOTO_FILENAMES = tf.io.gfile.glob(str(GCS_PATH + '/photo_tfrec/*.tfrec'))\n\nn_monet_samples = count_data_items(MONET_FILENAMES)\nn_photo_samples = count_data_items(PHOTO_FILENAMES)\n\nprint('Number of Monet TFRecord Files:', len(MONET_FILENAMES))\nprint('Number of Photo TFRecord Files:', len(PHOTO_FILENAMES))","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:11:26.196451Z","iopub.execute_input":"2021-11-07T13:11:26.196969Z","iopub.status.idle":"2021-11-07T13:11:26.372757Z","shell.execute_reply.started":"2021-11-07T13:11:26.196929Z","shell.execute_reply":"2021-11-07T13:11:26.371707Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"BUFFER_SIZE = 1000\nBATCH_SIZE =  4\nEPOCHS_NUM = 30\nIMG_WIDTH = 256\nIMG_HEIGHT = 256","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:11:34.429379Z","iopub.execute_input":"2021-11-07T13:11:34.430212Z","iopub.status.idle":"2021-11-07T13:11:34.434566Z","shell.execute_reply.started":"2021-11-07T13:11:34.430166Z","shell.execute_reply":"2021-11-07T13:11:34.433539Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def decode_image(image):\n    # Decode a JPEG-encoded image to a uint8 tensor.\n    image = tf.image.decode_jpeg(image, channels=3)\n    \n    # Normalize the image to the range of the tanh activation function [-1, 1] for \n    # inputs to the generator and discriminator in GAN model \n    # (i.e. the pixel values are divided by (255/2) to form a value of in a range of [0, 2] and then subtract by 1\n    # to result into a range of [-1, 1])\n    image = (tf.cast(image, tf.float32) / 127.5) - 1        \n    \n    # Reshape the tensor using (256, 256, 3) where 3 is number of channels: Red, Green, and Blue \n    image = tf.reshape(image, [IMG_HEIGHT, IMG_WIDTH, 3])             \n    return image\n\ndef read_tfrecord(example):\n    # Define TFRecord format \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    # Parse a single example\n    example = tf.io.parse_single_example(example, tfrecord_format)  \n    # Decode a JPEG image to a uint8 tensor by calling decode_image()\n    image = decode_image(example['image'])    \n    \n    return image # Return an image tensor","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:11:38.710835Z","iopub.execute_input":"2021-11-07T13:11:38.711587Z","iopub.status.idle":"2021-11-07T13:11:38.720195Z","shell.execute_reply.started":"2021-11-07T13:11:38.711546Z","shell.execute_reply":"2021-11-07T13:11:38.719195Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def data_augment(image):\n    p_rotate = tf.random.uniform([], 0, 1.0, dtype=tf.float32)\n    p_spatial = tf.random.uniform([], 0, 1.0, dtype=tf.float32)\n    p_crop = tf.random.uniform([], 0, 1.0, dtype=tf.float32)\n    \n    # Apply jitter\n    if p_crop > .5:\n        image = tf.image.resize(image, [286, 286])\n        image = tf.image.random_crop(image, size=[256, 256, 3])\n        if p_crop > .9:\n            image = tf.image.resize(image, [300, 300])\n            image = tf.image.random_crop(image, size=[256, 256, 3])\n    \n    # Random rotation\n    if p_rotate > .9:\n        image = tf.image.rot90(image, k=3) # rotate 270º\n    elif p_rotate > .7:\n        image = tf.image.rot90(image, k=2) # rotate 180º\n    elif p_rotate > .5:\n        image = tf.image.rot90(image, k=1) # rotate 90º\n    \n    # Random mirroring\n    if p_spatial > .6:\n        image = tf.image.random_flip_left_right(image)\n        image = tf.image.random_flip_up_down(image)\n        if p_spatial > .9:\n            image = tf.image.transpose(image)\n    \n    return image","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:11:54.697134Z","iopub.execute_input":"2021-11-07T13:11:54.697675Z","iopub.status.idle":"2021-11-07T13:11:54.707963Z","shell.execute_reply.started":"2021-11-07T13:11:54.697623Z","shell.execute_reply":"2021-11-07T13:11:54.707294Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Set it to tf.data.experimental.AUTOTUNE which will prompt \n# the tf.data runtime to tune the value dynamically at runtime.\nAUTOTUNE = tf.data.experimental.AUTOTUNE  \n\ndef load_dataset(filenames, labeled=True, ordered=False):\n    dataset = tf.data.TFRecordDataset(filenames)\n    # map a dataset with a mapping function read_tfrecord and \n    # Number of parallel calls is set to AUTOTUNE constant previously defined\n    dataset = dataset.map(read_tfrecord, num_parallel_calls=AUTOTUNE)\n    return dataset","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:12:02.691954Z","iopub.execute_input":"2021-11-07T13:12:02.692455Z","iopub.status.idle":"2021-11-07T13:12:02.698838Z","shell.execute_reply.started":"2021-11-07T13:12:02.692409Z","shell.execute_reply":"2021-11-07T13:12:02.697855Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"BATCHSIZE = 1\nmonet_ds = load_dataset(MONET_FILENAMES, labeled=True).batch(BATCHSIZE, drop_remainder=True)\nphoto_ds = load_dataset(PHOTO_FILENAMES, labeled=True).batch(BATCHSIZE, drop_remainder=True)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:12:10.392695Z","iopub.execute_input":"2021-11-07T13:12:10.393267Z","iopub.status.idle":"2021-11-07T13:12:10.577029Z","shell.execute_reply.started":"2021-11-07T13:12:10.393227Z","shell.execute_reply":"2021-11-07T13:12:10.576204Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_gan_dataset(monet_files, photo_files, augment=None, repeat=True, shuffle=True, batch_size=1):\n\n    monet_ds = load_dataset(monet_files)\n    photo_ds = load_dataset(photo_files)\n    \n    if augment:\n        monet_ds = monet_ds.map(augment, num_parallel_calls=AUTO)\n        photo_ds = photo_ds.map(augment, num_parallel_calls=AUTO)\n\n    if repeat:\n        monet_ds = monet_ds.repeat()\n        photo_ds = photo_ds.repeat()\n        \n    if shuffle:\n        monet_ds = monet_ds.shuffle(2048)\n        photo_ds = photo_ds.shuffle(2048)\n        \n    monet_ds = monet_ds.batch(batch_size, drop_remainder=True)\n    photo_ds = photo_ds.batch(batch_size, drop_remainder=True)\n    monet_ds = monet_ds.cache()\n    photo_ds = photo_ds.cache()\n    monet_ds = monet_ds.prefetch(AUTO)\n    photo_ds = photo_ds.prefetch(AUTO)\n    \n    gan_ds = tf.data.Dataset.zip((monet_ds, photo_ds))\n    \n    return gan_ds","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:12:20.335412Z","iopub.execute_input":"2021-11-07T13:12:20.335692Z","iopub.status.idle":"2021-11-07T13:12:20.344814Z","shell.execute_reply.started":"2021-11-07T13:12:20.335665Z","shell.execute_reply":"2021-11-07T13:12:20.343874Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"full_dataset = get_gan_dataset(MONET_FILENAMES, PHOTO_FILENAMES, augment=data_augment, repeat=True, shuffle=True, batch_size=BATCH_SIZE)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:12:33.622095Z","iopub.execute_input":"2021-11-07T13:12:33.622583Z","iopub.status.idle":"2021-11-07T13:12:34.497317Z","shell.execute_reply.started":"2021-11-07T13:12:33.622530Z","shell.execute_reply":"2021-11-07T13:12:34.496377Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"example_monet , example_photo = next(iter(full_dataset))","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:12:38.861123Z","iopub.execute_input":"2021-11-07T13:12:38.861450Z","iopub.status.idle":"2021-11-07T13:12:44.695915Z","shell.execute_reply.started":"2021-11-07T13:12:38.861417Z","shell.execute_reply":"2021-11-07T13:12:44.695080Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def view_image(ds, nrows=1, ncols=5):\n    ds_iter = iter(ds)\n    # image = next(iter(ds)) # extract 1 from the dataset\n    # image = image.numpy()  # convert the image tensor to NumPy ndarrays.\n\n    fig = plt.figure(figsize=(25, nrows * 5.05 )) # figsize with Width, Height\n    \n    # loop thru all the images (number of rows * number of columns)\n    for i in range(ncols * nrows):\n        image = next(ds_iter)\n        image = image.numpy()\n        ax = fig.add_subplot(nrows, ncols, i+1, xticks=[], yticks=[])\n        ax.imshow(image[0] * 0.5 + .5) # rescale the data in [0, 1] for display","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:12:51.681962Z","iopub.execute_input":"2021-11-07T13:12:51.682474Z","iopub.status.idle":"2021-11-07T13:12:51.689974Z","shell.execute_reply.started":"2021-11-07T13:12:51.682436Z","shell.execute_reply":"2021-11-07T13:12:51.689062Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"view_image(monet_ds,2, 5)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:12:56.026090Z","iopub.execute_input":"2021-11-07T13:12:56.026353Z","iopub.status.idle":"2021-11-07T13:12:57.163919Z","shell.execute_reply.started":"2021-11-07T13:12:56.026327Z","shell.execute_reply":"2021-11-07T13:12:57.163148Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"view_image(photo_ds,2, 5)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:13:01.620983Z","iopub.execute_input":"2021-11-07T13:13:01.621454Z","iopub.status.idle":"2021-11-07T13:13:03.032680Z","shell.execute_reply.started":"2021-11-07T13:13:01.621407Z","shell.execute_reply":"2021-11-07T13:13:03.031901Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Build the generator","metadata":{}},{"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    gamma_init = keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n\n    result = keras.Sequential()\n    result.add(layers.Conv2D(filters, size, strides=2, padding='same',\n                             kernel_initializer=initializer, use_bias=False))\n\n    if apply_instancenorm:\n        result.add(tfa.layers.InstanceNormalization(gamma_initializer=gamma_init))\n\n    result.add(layers.LeakyReLU())\n\n    return result","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:13:08.630569Z","iopub.execute_input":"2021-11-07T13:13:08.631425Z","iopub.status.idle":"2021-11-07T13:13:08.637586Z","shell.execute_reply.started":"2021-11-07T13:13:08.631386Z","shell.execute_reply":"2021-11-07T13:13:08.636871Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def upsample(filters, size, apply_dropout=False):\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gamma_init = keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n\n    result = keras.Sequential()\n    result.add(layers.Conv2DTranspose(filters, size, strides=2,\n                                      padding='same',\n                                      kernel_initializer=initializer,\n                                      use_bias=False))\n\n    result.add(tfa.layers.InstanceNormalization(gamma_initializer=gamma_init))\n\n    if apply_dropout:\n        result.add(layers.Dropout(0.5))\n\n    result.add(layers.ReLU())\n\n    return result","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:13:12.528251Z","iopub.execute_input":"2021-11-07T13:13:12.528567Z","iopub.status.idle":"2021-11-07T13:13:12.535701Z","shell.execute_reply.started":"2021-11-07T13:13:12.528521Z","shell.execute_reply":"2021-11-07T13:13:12.534824Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def Generator():\n    inputs = layers.Input(shape=[256,256,3])\n\n    # bs = batch size\n    down_stack = [\n        downsample(64, 4, apply_instancenorm=False), # (bs, 128, 128, 64)\n        downsample(128, 4), # (bs, 64, 64, 128)\n        downsample(256, 4), # (bs, 32, 32, 256)\n        downsample(512, 4), # (bs, 16, 16, 512)\n        downsample(512, 4), # (bs, 8, 8, 512)\n        downsample(512, 4), # (bs, 4, 4, 512)\n        downsample(512, 4), # (bs, 2, 2, 512)\n        downsample(512, 4), # (bs, 1, 1, 512)\n    ]\n\n    up_stack = [\n        upsample(512, 4, apply_dropout=True), # (bs, 2, 2, 1024)\n        upsample(512, 4, apply_dropout=True), # (bs, 4, 4, 1024)\n        upsample(512, 4, apply_dropout=True), # (bs, 8, 8, 1024)\n        upsample(512, 4), # (bs, 16, 16, 1024)\n        upsample(256, 4), # (bs, 32, 32, 512)\n        upsample(128, 4), # (bs, 64, 64, 256)\n        upsample(64, 4), # (bs, 128, 128, 128)\n    ]\n\n    initializer = tf.random_normal_initializer(0., 0.02)\n    last = layers.Conv2DTranspose(OUTPUT_CHANNELS, 4,\n                                  strides=2,\n                                  padding='same',\n                                  kernel_initializer=initializer,\n                                  activation='tanh') # (bs, 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 = layers.Concatenate()([x, skip])\n\n    x = last(x)\n\n    return keras.Model(inputs=inputs, outputs=x)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:13:16.355135Z","iopub.execute_input":"2021-11-07T13:13:16.355991Z","iopub.status.idle":"2021-11-07T13:13:16.368299Z","shell.execute_reply.started":"2021-11-07T13:13:16.355936Z","shell.execute_reply":"2021-11-07T13:13:16.367484Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Build the discriminator","metadata":{}},{"cell_type":"code","source":"def Discriminator():\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gamma_init = keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n\n    inp = layers.Input(shape=[256, 256, 3], name='input_image')\n\n    x = inp\n\n    down1 = downsample(64, 4, False)(x) # (bs, 128, 128, 64)\n    down2 = downsample(128, 4)(down1) # (bs, 64, 64, 128)\n    down3 = downsample(256, 4)(down2) # (bs, 32, 32, 256)\n\n    zero_pad1 = layers.ZeroPadding2D()(down3) # (bs, 34, 34, 256)\n    conv = layers.Conv2D(512, 4, strides=1,\n                         kernel_initializer=initializer,\n                         use_bias=False)(zero_pad1) # (bs, 31, 31, 512)\n\n    norm1 = tfa.layers.InstanceNormalization(gamma_initializer=gamma_init)(conv)\n\n    leaky_relu = layers.LeakyReLU()(norm1)\n\n    zero_pad2 = layers.ZeroPadding2D()(leaky_relu) # (bs, 33, 33, 512)\n\n    last = layers.Conv2D(1, 4, strides=1,\n                         kernel_initializer=initializer)(zero_pad2) # (bs, 30, 30, 1)\n\n    return tf.keras.Model(inputs=inp, outputs=last)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:13:20.991612Z","iopub.execute_input":"2021-11-07T13:13:20.991887Z","iopub.status.idle":"2021-11-07T13:13:21.001183Z","shell.execute_reply.started":"2021-11-07T13:13:20.991860Z","shell.execute_reply":"2021-11-07T13:13:21.000215Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    monet_generator = Generator() # transforms photos to Monet-esque paintings\n    photo_generator = Generator() # transforms Monet paintings to be more like photos\n\n    monet_discriminator = Discriminator() # differentiates real Monet paintings and generated Monet paintings\n    photo_discriminator = Discriminator() # differentiates real photos and generated photos","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:13:28.024288Z","iopub.execute_input":"2021-11-07T13:13:28.024578Z","iopub.status.idle":"2021-11-07T13:13:37.526198Z","shell.execute_reply.started":"2021-11-07T13:13:28.024548Z","shell.execute_reply":"2021-11-07T13:13:37.525535Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"to_monet = monet_generator(example_photo)\n\nplt.subplot(1, 2, 1)\nplt.title(\"Original Photo\")\nplt.imshow(example_photo[0] * 0.5 + 0.5)\n\nplt.subplot(1, 2, 2)\nplt.title(\"Monet-esque Photo\")\nplt.imshow(to_monet[0] * 0.5 + 0.5)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:13:42.250710Z","iopub.execute_input":"2021-11-07T13:13:42.251605Z","iopub.status.idle":"2021-11-07T13:13:43.029465Z","shell.execute_reply.started":"2021-11-07T13:13:42.251569Z","shell.execute_reply":"2021-11-07T13:13:43.028554Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Build the CycleGAN model","metadata":{}},{"cell_type":"code","source":"class CycleGan(keras.Model):\n    def __init__(\n        self,\n        monet_generator,\n        photo_generator,\n        monet_discriminator,\n        photo_discriminator,\n        lambda_cycle=10,\n    ):\n        super(CycleGan, self).__init__()\n        self.m_gen = monet_generator\n        self.p_gen = photo_generator\n        self.m_disc = monet_discriminator\n        self.p_disc = photo_discriminator\n        self.lambda_cycle = lambda_cycle\n        \n    def compile(\n        self,\n        m_gen_optimizer,\n        p_gen_optimizer,\n        m_disc_optimizer,\n        p_disc_optimizer,\n        gen_loss_fn,\n        disc_loss_fn,\n        cycle_loss_fn,\n        identity_loss_fn\n    ):\n        super(CycleGan, self).compile()\n        self.m_gen_optimizer = m_gen_optimizer\n        self.p_gen_optimizer = p_gen_optimizer\n        self.m_disc_optimizer = m_disc_optimizer\n        self.p_disc_optimizer = p_disc_optimizer\n        self.gen_loss_fn = gen_loss_fn\n        self.disc_loss_fn = disc_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            # photo to monet back to photo\n            fake_monet = self.m_gen(real_photo, training=True)\n            cycled_photo = self.p_gen(fake_monet, training=True)\n\n            # monet to photo back to monet\n            fake_photo = self.p_gen(real_monet, training=True)\n            cycled_monet = self.m_gen(fake_photo, training=True)\n\n            # generating itself\n            same_monet = self.m_gen(real_monet, training=True)\n            same_photo = self.p_gen(real_photo, training=True)\n\n            # discriminator used to check, inputing real images\n            disc_real_monet = self.m_disc(real_monet, training=True)\n            disc_real_photo = self.p_disc(real_photo, training=True)\n\n            # discriminator used to check, inputing fake images\n            disc_fake_monet = self.m_disc(fake_monet, training=True)\n            disc_fake_photo = self.p_disc(fake_photo, training=True)\n\n            # evaluates generator loss\n            monet_gen_loss = self.gen_loss_fn(disc_fake_monet)\n            photo_gen_loss = self.gen_loss_fn(disc_fake_photo)\n\n            # evaluates total cycle consistency loss\n            total_cycle_loss = self.cycle_loss_fn(real_monet, cycled_monet, self.lambda_cycle) + self.cycle_loss_fn(real_photo, cycled_photo, self.lambda_cycle)\n\n            # evaluates total generator loss\n            total_monet_gen_loss = monet_gen_loss + total_cycle_loss + self.identity_loss_fn(real_monet, same_monet, self.lambda_cycle)\n            total_photo_gen_loss = photo_gen_loss + total_cycle_loss + self.identity_loss_fn(real_photo, same_photo, self.lambda_cycle)\n\n            # evaluates discriminator loss\n            monet_disc_loss = self.disc_loss_fn(disc_real_monet, disc_fake_monet)\n            photo_disc_loss = self.disc_loss_fn(disc_real_photo, disc_fake_photo)\n\n        # Calculate the gradients for generator and discriminator\n        monet_generator_gradients = tape.gradient(total_monet_gen_loss,\n                                                  self.m_gen.trainable_variables)\n        photo_generator_gradients = tape.gradient(total_photo_gen_loss,\n                                                  self.p_gen.trainable_variables)\n\n        monet_discriminator_gradients = tape.gradient(monet_disc_loss,\n                                                      self.m_disc.trainable_variables)\n        photo_discriminator_gradients = tape.gradient(photo_disc_loss,\n                                                      self.p_disc.trainable_variables)\n\n        # Apply the gradients to the optimizer\n        self.m_gen_optimizer.apply_gradients(zip(monet_generator_gradients,\n                                                 self.m_gen.trainable_variables))\n\n        self.p_gen_optimizer.apply_gradients(zip(photo_generator_gradients,\n                                                 self.p_gen.trainable_variables))\n\n        self.m_disc_optimizer.apply_gradients(zip(monet_discriminator_gradients,\n                                                  self.m_disc.trainable_variables))\n\n        self.p_disc_optimizer.apply_gradients(zip(photo_discriminator_gradients,\n                                                  self.p_disc.trainable_variables))\n        \n        return {\n            \"monet_gen_loss\": total_monet_gen_loss,\n            \"photo_gen_loss\": total_photo_gen_loss,\n            \"monet_disc_loss\": monet_disc_loss,\n            \"photo_disc_loss\": photo_disc_loss\n        }","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:13:49.994847Z","iopub.execute_input":"2021-11-07T13:13:49.995340Z","iopub.status.idle":"2021-11-07T13:13:50.015746Z","shell.execute_reply.started":"2021-11-07T13:13:49.995304Z","shell.execute_reply":"2021-11-07T13:13:50.014633Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Loss functions","metadata":{}},{"cell_type":"code","source":"with strategy.scope():\n    # Discriminator loss {0: fake, 1: real} (The discriminator loss outputs the average of the real and generated loss)\n    def discriminator_loss(real, generated):\n        real_loss = losses.BinaryCrossentropy(from_logits=True, reduction=losses.Reduction.NONE)(tf.ones_like(real), real)\n\n        generated_loss = losses.BinaryCrossentropy(from_logits=True, reduction=losses.Reduction.NONE)(tf.zeros_like(generated), generated)\n\n        total_disc_loss = real_loss + generated_loss\n\n        return total_disc_loss * 0.5\n    \n    # Generator loss\n    def generator_loss(generated):\n        return losses.BinaryCrossentropy(from_logits=True, reduction=losses.Reduction.NONE)(tf.ones_like(generated), generated)\n    \n    \n    # Cycle consistency loss (measures if original photo and the twice transformed photo to be similar to one another)\n    with strategy.scope():\n        def calc_cycle_loss(real_image, cycled_image, LAMBDA):\n            loss1 = tf.reduce_mean(tf.abs(real_image - cycled_image))\n\n            return LAMBDA * loss1\n\n    # Identity loss (compares the image with its generator (i.e. photo with photo generator))\n    with strategy.scope():\n        def identity_loss(real_image, same_image, LAMBDA):\n            loss = tf.reduce_mean(tf.abs(real_image - same_image))\n            return LAMBDA * 0.5 * loss","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:13:56.077911Z","iopub.execute_input":"2021-11-07T13:13:56.078857Z","iopub.status.idle":"2021-11-07T13:13:56.088072Z","shell.execute_reply.started":"2021-11-07T13:13:56.078818Z","shell.execute_reply":"2021-11-07T13:13:56.087281Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    monet_generator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n    photo_generator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n\n    monet_discriminator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n    photo_discriminator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:14:00.247420Z","iopub.execute_input":"2021-11-07T13:14:00.248112Z","iopub.status.idle":"2021-11-07T13:14:00.254802Z","shell.execute_reply.started":"2021-11-07T13:14:00.248068Z","shell.execute_reply":"2021-11-07T13:14:00.253638Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    cycle_gan_model = CycleGan(\n        monet_generator, photo_generator, \n        monet_discriminator, photo_discriminator\n    )\n\n    cycle_gan_model.compile(\n        m_gen_optimizer = monet_generator_optimizer,\n        p_gen_optimizer = photo_generator_optimizer,\n        m_disc_optimizer = monet_discriminator_optimizer,\n        p_disc_optimizer = photo_discriminator_optimizer,\n        gen_loss_fn = generator_loss,\n        disc_loss_fn = discriminator_loss,\n        cycle_loss_fn = calc_cycle_loss,\n        identity_loss_fn = identity_loss\n    )","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:14:02.829030Z","iopub.execute_input":"2021-11-07T13:14:02.829614Z","iopub.status.idle":"2021-11-07T13:14:02.885246Z","shell.execute_reply.started":"2021-11-07T13:14:02.829548Z","shell.execute_reply":"2021-11-07T13:14:02.884262Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cycle_gan_model.fit(\n    full_dataset,\n    epochs=EPOCHS_NUM,\n    steps_per_epoch=(max(n_monet_samples, n_photo_samples)//BATCH_SIZE),\n)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T13:14:05.536816Z","iopub.execute_input":"2021-11-07T13:14:05.537547Z","iopub.status.idle":"2021-11-07T15:06:44.657679Z","shell.execute_reply.started":"2021-11-07T13:14:05.537503Z","shell.execute_reply":"2021-11-07T15:06:44.655849Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Display generated photos","metadata":{}},{"cell_type":"code","source":"def display_generated_samples(ds, model, n_samples):\n    ds_iter = iter(ds)\n    for n_sample in range(n_samples):\n        example_sample = next(ds_iter)\n        generated_sample = model.predict(example_sample)\n    \n        plt.subplot(121)\n        plt.title(\"Input image\")\n        plt.imshow(example_sample[0] * 0.5 + 0.5)\n        plt.axis('off')\n\n        plt.subplot(122)\n        plt.title(\"Generated image\")\n        plt.imshow(generated_sample[0] * 0.5 + 0.5)\n        plt.axis('off')\n        plt.show()","metadata":{"execution":{"iopub.status.busy":"2021-11-07T15:06:54.539727Z","iopub.execute_input":"2021-11-07T15:06:54.540186Z","iopub.status.idle":"2021-11-07T15:06:54.554090Z","shell.execute_reply.started":"2021-11-07T15:06:54.540136Z","shell.execute_reply":"2021-11-07T15:06:54.553051Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_generated_samples(load_dataset(PHOTO_FILENAMES).batch(1), monet_generator, 7)","metadata":{"execution":{"iopub.status.busy":"2021-11-07T15:06:58.601219Z","iopub.execute_input":"2021-11-07T15:06:58.602025Z","iopub.status.idle":"2021-11-07T15:07:09.669408Z","shell.execute_reply.started":"2021-11-07T15:06:58.601982Z","shell.execute_reply":"2021-11-07T15:07:09.668510Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Predict and save the images","metadata":{}},{"cell_type":"code","source":"import PIL\ndef predict_and_save(input_ds, generator_model, output_path):\n    i = 1\n    for img in input_ds:\n        prediction = generator_model(img, training=False)[0].numpy() # make predition\n        prediction = (prediction * 127.5 + 127.5).astype(np.uint8)   # re-scale\n        im = PIL.Image.fromarray(prediction)\n        im.save(f'{output_path}{str(i)}.jpg')\n        i += 1","metadata":{"execution":{"iopub.status.busy":"2021-11-07T15:08:00.678270Z","iopub.execute_input":"2021-11-07T15:08:00.678561Z","iopub.status.idle":"2021-11-07T15:08:00.686477Z","shell.execute_reply.started":"2021-11-07T15:08:00.678532Z","shell.execute_reply":"2021-11-07T15:08:00.685386Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nos.makedirs('../images/') # Create folder to save generated images\n\npredict_and_save(load_dataset(PHOTO_FILENAMES).batch(1), monet_generator, '../images/')","metadata":{"execution":{"iopub.status.busy":"2021-11-07T15:08:07.818592Z","iopub.execute_input":"2021-11-07T15:08:07.819294Z","iopub.status.idle":"2021-11-07T15:42:57.941328Z","shell.execute_reply.started":"2021-11-07T15:08:07.819239Z","shell.execute_reply":"2021-11-07T15:42:57.939477Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import shutil\nshutil.make_archive('/kaggle/working/images/', 'zip', '../images')\n\nprint(f\"Number of generated samples: {len([name for name in os.listdir('../images/') if os.path.isfile(os.path.join('../images/', name))])}\")","metadata":{"execution":{"iopub.status.busy":"2021-11-07T15:43:07.950957Z","iopub.execute_input":"2021-11-07T15:43:07.952351Z","iopub.status.idle":"2021-11-07T15:43:12.530773Z","shell.execute_reply.started":"2021-11-07T15:43:07.952296Z","shell.execute_reply":"2021-11-07T15:43:12.529589Z"},"trusted":true},"execution_count":null,"outputs":[]}]}