{"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":"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":"2021-07-14T05:17:11.219698Z","iopub.execute_input":"2021-07-14T05:17:11.220411Z","iopub.status.idle":"2021-07-14T05:17:12.268013Z","shell.execute_reply.started":"2021-07-14T05:17:11.220361Z","shell.execute_reply":"2021-07-14T05:17:12.266725Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nimport tensorflow_addons as tfa\n\nfrom kaggle_datasets import KaggleDatasets\nimport matplotlib.pyplot as plt\nimport numpy as np\n\ntry:\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.experimental.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(tf.__version__)","metadata":{"execution":{"iopub.status.busy":"2021-07-14T05:17:22.998893Z","iopub.execute_input":"2021-07-14T05:17:22.999309Z","iopub.status.idle":"2021-07-14T05:17:23.010203Z","shell.execute_reply.started":"2021-07-14T05:17:22.999271Z","shell.execute_reply":"2021-07-14T05:17:23.008607Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GCS_PATH = KaggleDatasets().get_gcs_path()","metadata":{"execution":{"iopub.status.busy":"2021-07-14T05:17:27.337644Z","iopub.execute_input":"2021-07-14T05:17:27.33807Z","iopub.status.idle":"2021-07-14T05:17:27.648216Z","shell.execute_reply.started":"2021-07-14T05:17:27.338034Z","shell.execute_reply":"2021-07-14T05:17:27.647272Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"MONET_FILENAMES = tf.io.gfile.glob(str(GCS_PATH + '/monet_tfrec/*.tfrec'))\nprint('Monet TFRecord Files:', len(MONET_FILENAMES))\n\nPHOTO_FILENAMES = tf.io.gfile.glob(str(GCS_PATH + '/photo_tfrec/*.tfrec'))\nprint('Photo TFRecord Files:', len(PHOTO_FILENAMES))","metadata":{"execution":{"iopub.status.busy":"2021-07-14T05:17:30.018273Z","iopub.execute_input":"2021-07-14T05:17:30.018985Z","iopub.status.idle":"2021-07-14T05:17:30.231044Z","shell.execute_reply.started":"2021-07-14T05:17:30.018941Z","shell.execute_reply":"2021-07-14T05:17:30.229892Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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","metadata":{"execution":{"iopub.status.busy":"2021-07-14T05:18:37.678302Z","iopub.execute_input":"2021-07-14T05:18:37.678764Z","iopub.status.idle":"2021-07-14T05:18:37.688634Z","shell.execute_reply.started":"2021-07-14T05:18:37.678722Z","shell.execute_reply":"2021-07-14T05:18:37.687195Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def load_dataset(filenames, labeled=True, ordered=False):\n    dataset = tf.data.TFRecordDataset(filenames)\n    dataset = dataset.map(read_tfrecord, num_parallel_calls=AUTOTUNE)\n    return dataset","metadata":{"execution":{"iopub.status.busy":"2021-07-14T05:18:47.858849Z","iopub.execute_input":"2021-07-14T05:18:47.859285Z","iopub.status.idle":"2021-07-14T05:18:47.865401Z","shell.execute_reply.started":"2021-07-14T05:18:47.859247Z","shell.execute_reply":"2021-07-14T05:18:47.864298Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"monet_ds = load_dataset(MONET_FILENAMES, labeled=True).batch(1)\nphoto_ds = load_dataset(PHOTO_FILENAMES, labeled=True).batch(1)","metadata":{"execution":{"iopub.status.busy":"2021-07-14T05:18:59.318368Z","iopub.execute_input":"2021-07-14T05:18:59.319211Z","iopub.status.idle":"2021-07-14T05:18:59.704395Z","shell.execute_reply.started":"2021-07-14T05:18:59.319147Z","shell.execute_reply":"2021-07-14T05:18:59.703087Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"example_monet = next(iter(monet_ds))\nexample_photo = next(iter(photo_ds))","metadata":{"execution":{"iopub.status.busy":"2021-07-14T05:19:08.598673Z","iopub.execute_input":"2021-07-14T05:19:08.599481Z","iopub.status.idle":"2021-07-14T05:19:09.591675Z","shell.execute_reply.started":"2021-07-14T05:19:08.599428Z","shell.execute_reply":"2021-07-14T05:19:09.590317Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.subplot(121)\nplt.title('Photo')\nplt.imshow(example_photo[0] * 0.5 + 0.5)\n\nplt.subplot(122)\nplt.title('Monet')\nplt.imshow(example_monet[0] * 0.5 + 0.5)\n","metadata":{"execution":{"iopub.status.busy":"2021-07-14T05:19:36.538067Z","iopub.execute_input":"2021-07-14T05:19:36.538706Z","iopub.status.idle":"2021-07-14T05:19:36.980635Z","shell.execute_reply.started":"2021-07-14T05:19:36.538667Z","shell.execute_reply":"2021-07-14T05:19:36.979529Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2021-07-14T05:21:24.779252Z","iopub.execute_input":"2021-07-14T05:21:24.780214Z","iopub.status.idle":"2021-07-14T05:21:24.786946Z","shell.execute_reply.started":"2021-07-14T05:21:24.780144Z","shell.execute_reply":"2021-07-14T05:21:24.786038Z"},"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":"2021-07-14T05:21:39.2285Z","iopub.execute_input":"2021-07-14T05:21:39.228944Z","iopub.status.idle":"2021-07-14T05:21:39.237943Z","shell.execute_reply.started":"2021-07-14T05:21:39.228906Z","shell.execute_reply":"2021-07-14T05:21:39.23698Z"},"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":"2021-07-14T05:21:52.802544Z","iopub.execute_input":"2021-07-14T05:21:52.803161Z","iopub.status.idle":"2021-07-14T05:21:52.813709Z","shell.execute_reply.started":"2021-07-14T05:21:52.803109Z","shell.execute_reply":"2021-07-14T05:21:52.812423Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2021-07-14T05:22:11.878275Z","iopub.execute_input":"2021-07-14T05:22:11.87881Z","iopub.status.idle":"2021-07-14T05:22:11.889305Z","shell.execute_reply.started":"2021-07-14T05:22:11.878754Z","shell.execute_reply":"2021-07-14T05:22:11.887286Z"},"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":"2021-07-14T05:22:25.5387Z","iopub.execute_input":"2021-07-14T05:22:25.539301Z","iopub.status.idle":"2021-07-14T05:22:31.338026Z","shell.execute_reply.started":"2021-07-14T05:22:25.53925Z","shell.execute_reply":"2021-07-14T05:22:31.336823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}