{"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\n# for 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":"2022-11-07T05:13:03.179141Z","iopub.execute_input":"2022-11-07T05:13:03.179431Z","iopub.status.idle":"2022-11-07T05:13:03.184555Z","shell.execute_reply.started":"2022-11-07T05:13:03.179403Z","shell.execute_reply":"2022-11-07T05:13:03.183505Z"},"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\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\nprint(tf.__version__)    ","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:03.220639Z","iopub.execute_input":"2022-11-07T05:13:03.221184Z","iopub.status.idle":"2022-11-07T05:13:13.743042Z","shell.execute_reply.started":"2022-11-07T05:13:03.221123Z","shell.execute_reply":"2022-11-07T05:13:13.741980Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GCS_PATH = KaggleDatasets().get_gcs_path()","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:13.744359Z","iopub.execute_input":"2022-11-07T05:13:13.744597Z","iopub.status.idle":"2022-11-07T05:13:14.114416Z","shell.execute_reply.started":"2022-11-07T05:13:13.744558Z","shell.execute_reply":"2022-11-07T05:13:14.113489Z"},"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":"2022-11-07T05:13:14.115518Z","iopub.execute_input":"2022-11-07T05:13:14.115766Z","iopub.status.idle":"2022-11-07T05:13:14.266272Z","shell.execute_reply.started":"2022-11-07T05:13:14.115739Z","shell.execute_reply":"2022-11-07T05:13:14.265687Z"},"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]) # tf.reshape(image, [256, 256, 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=AUTOTUNE)\n    return dataset","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:14.268265Z","iopub.execute_input":"2022-11-07T05:13:14.268516Z","iopub.status.idle":"2022-11-07T05:13:14.277561Z","shell.execute_reply.started":"2022-11-07T05:13:14.268486Z","shell.execute_reply":"2022-11-07T05:13:14.276897Z"},"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":"2022-11-07T05:13:14.278544Z","iopub.execute_input":"2022-11-07T05:13:14.278836Z","iopub.status.idle":"2022-11-07T05:13:14.387930Z","shell.execute_reply.started":"2022-11-07T05:13:14.278799Z","shell.execute_reply":"2022-11-07T05:13:14.386831Z"},"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":"2022-11-07T05:13:14.389094Z","iopub.execute_input":"2022-11-07T05:13:14.389340Z","iopub.status.idle":"2022-11-07T05:13:14.481963Z","shell.execute_reply.started":"2022-11-07T05:13:14.389311Z","shell.execute_reply":"2022-11-07T05:13:14.480993Z"},"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)","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:14.483253Z","iopub.execute_input":"2022-11-07T05:13:14.484103Z","iopub.status.idle":"2022-11-07T05:13:14.881048Z","shell.execute_reply.started":"2022-11-07T05:13:14.484058Z","shell.execute_reply":"2022-11-07T05:13:14.880016Z"},"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    result.add(layers.LeakyReLU())\n    return result","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:14.882418Z","iopub.execute_input":"2022-11-07T05:13:14.882709Z","iopub.status.idle":"2022-11-07T05:13:14.889717Z","shell.execute_reply.started":"2022-11-07T05:13:14.882676Z","shell.execute_reply":"2022-11-07T05:13:14.888735Z"},"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    result.add(tfa.layers.InstanceNormalization(gamma_initializer=gamma_init))\n    \n    if apply_dropout:\n        result.add(layers.Dropout(0.5))\n    result.add(layers.ReLU())\n    return result","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:14.891505Z","iopub.execute_input":"2022-11-07T05:13:14.891806Z","iopub.status.idle":"2022-11-07T05:13:14.904881Z","shell.execute_reply.started":"2022-11-07T05:13:14.891773Z","shell.execute_reply":"2022-11-07T05:13:14.903770Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def Generator():\n    inputs = layers.Input(shape=[256, 256, 3])\n    \n    down_stack = [\n        # Same padding makes input size and output size at the same\n        # only if strides was 1 ... (I-1)/S + 1\n        # Same padding P is (K-1)/2\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),\n        upsample(512, 4, apply_dropout=True),\n        upsample(512, 4, apply_dropout=True),\n        upsample(512, 4),\n        upsample(256, 4),\n        upsample(128, 4),\n        upsample(64, 4),\n    ]\n    \n    initializer = tf.random_normal_initializer(0., 0.02)\n    last = layers.Conv2DTranspose(OUTPUT_CHANNELS, 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 = layers.Concatenate()([x, skip])\n        \n    x = last(x)\n    \n    return keras.Model(inputs=inputs, outputs=x)","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:14.908487Z","iopub.execute_input":"2022-11-07T05:13:14.908878Z","iopub.status.idle":"2022-11-07T05:13:14.921230Z","shell.execute_reply.started":"2022-11-07T05:13:14.908842Z","shell.execute_reply":"2022-11-07T05:13:14.920001Z"},"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    inputs = layers.Input(shape=[256, 256, 3], name='input_image')\n    \n    x = inputs\n    \n    down1 = downsample(64, 4, False)(x)\n    down2 = downsample(128, 4)(down1)\n    down3 = downsample(256, 4)(down2)\n    \n    zero_pad1 = layers.ZeroPadding2D()(down3)\n    conv = layers.Conv2D(512, 4, strides=1,\n                        kernel_initializer=initializer,\n                        use_bias=False)(zero_pad1)\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)\n    \n    last = layers.Conv2D(1, 4, strides=1,\n                        kernel_initializer=initializer)(zero_pad2)\n    \n    return tf.keras.Model(inputs=inputs, outputs=last)","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:14.922533Z","iopub.execute_input":"2022-11-07T05:13:14.922842Z","iopub.status.idle":"2022-11-07T05:13:14.937694Z","shell.execute_reply.started":"2022-11-07T05:13:14.922811Z","shell.execute_reply":"2022-11-07T05:13:14.936482Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    monet_generator = Generator()\n    photo_generator = Generator()\n    \n    monet_discriminator = Discriminator()\n    photo_discriminator = Discriminator()","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:14.939333Z","iopub.execute_input":"2022-11-07T05:13:14.939907Z","iopub.status.idle":"2022-11-07T05:13:19.992358Z","shell.execute_reply.started":"2022-11-07T05:13:14.939864Z","shell.execute_reply":"2022-11-07T05:13:19.991482Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"to_monet = monet_generator(example_photo)\n\nplt.subplot(121)\nplt.title(\"Original Photo\")\nplt.imshow(example_photo[0] * 0.5 + 0.5)\n\nplt.subplot(122)\nplt.title(\"Monet-esque Photo\")\nplt.imshow(to_monet[0] * 0.5 + 0.5)\n\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:19.993569Z","iopub.execute_input":"2022-11-07T05:13:19.993949Z","iopub.status.idle":"2022-11-07T05:13:20.619912Z","shell.execute_reply.started":"2022-11-07T05:13:19.993920Z","shell.execute_reply":"2022-11-07T05:13:20.618951Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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            fake_monet = self.m_gen(real_photo, training=True)\n            cycled_photo = self.p_gen(fake_monet, training=True)\n            \n            fake_photo = self.p_gen(real_monet, training=True)\n            cycled_monet = self.m_gen(fake_photo, training=True)\n            \n            same_monet = self.m_gen(real_monet, training=True)\n            same_photo = self.p_gen(real_photo, training=True)\n            \n            disc_real_monet = self.m_disc(real_monet, training=True)\n            disc_real_photo = self.p_disc(real_photo, training=True)\n            \n            disc_fake_monet = self.m_disc(fake_monet, training=True)\n            disc_fake_photo = self.p_disc(fake_photo, training=True)\n            \n            monet_gen_loss = self.gen_loss_fn(disc_fake_monet)\n            photo_gen_loss = self.gen_loss_fn(disc_fake_photo)\n            \n            total_cycle_loss =\\\n                self.cycle_loss_fn(real_monet, cycled_monet, self.lambda_cycle) +\\\n                self.cycle_loss_fn(real_photo, cycled_photo, self.lambda_cycle)\n            \n            total_monet_gen_loss = monet_gen_loss + total_cycle_loss +\\\n                self.identity_loss_fn(real_monet, same_monet, self.lambda_cycle)\n            total_photo_gen_loss = photo_gen_loss + total_cycle_loss +\\\n                self.identity_loss_fn(real_photo, same_photo, self.lambda_cycle)\n            \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            \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        self.m_gen_optimizer.apply_gradients(zip(monet_generator_gradients,\n                                                self.m_gen.trainable_variables))\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        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":"2022-11-07T05:13:20.621277Z","iopub.execute_input":"2022-11-07T05:13:20.621518Z","iopub.status.idle":"2022-11-07T05:13:20.639852Z","shell.execute_reply.started":"2022-11-07T05:13:20.621489Z","shell.execute_reply":"2022-11-07T05:13:20.638638Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    def discriminator_loss(real, generated):\n        real_loss = tf.keras.losses.BinaryCrossentropy(from_logits=True,\n                                                      reduction=tf.keras.losses.Reduction.NONE)(tf.ones_like(real), real)\n        generated_loss = tf.keras.losses.BinaryCrossentropy(from_logits=True,\n                                                           reduction=tf.keras.losses.Reduction.NONE)(tf.zeros_like(generated), generated)\n        total_disc_loss = real_loss + generated_loss\n        \n        return total_disc_loss * 0.5","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:20.641525Z","iopub.execute_input":"2022-11-07T05:13:20.642187Z","iopub.status.idle":"2022-11-07T05:13:20.654793Z","shell.execute_reply.started":"2022-11-07T05:13:20.642141Z","shell.execute_reply":"2022-11-07T05:13:20.653361Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    def generator_loss(generated):\n        return tf.keras.losses.BinaryCrossentropy(from_logits=True,\n                                                 reduction=tf.keras.losses.Reduction.NONE)(tf.ones_like(generated), generated)","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:20.656237Z","iopub.execute_input":"2022-11-07T05:13:20.656684Z","iopub.status.idle":"2022-11-07T05:13:20.669659Z","shell.execute_reply.started":"2022-11-07T05:13:20.656632Z","shell.execute_reply":"2022-11-07T05:13:20.668884Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    def calc_cycle_loss(real_image, cycled_image, LAMBDA):\n        loss = tf.reduce_mean(tf.abs(real_image - cycled_image))\n        \n        return LAMBDA * loss","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:20.670632Z","iopub.execute_input":"2022-11-07T05:13:20.671269Z","iopub.status.idle":"2022-11-07T05:13:20.681822Z","shell.execute_reply.started":"2022-11-07T05:13:20.671235Z","shell.execute_reply":"2022-11-07T05:13:20.681011Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"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":"2022-11-07T05:13:20.682858Z","iopub.execute_input":"2022-11-07T05:13:20.683801Z","iopub.status.idle":"2022-11-07T05:13:20.694546Z","shell.execute_reply.started":"2022-11-07T05:13:20.683761Z","shell.execute_reply":"2022-11-07T05:13:20.693890Z"},"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    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":"2022-11-07T05:13:20.696147Z","iopub.execute_input":"2022-11-07T05:13:20.696550Z","iopub.status.idle":"2022-11-07T05:13:20.706140Z","shell.execute_reply.started":"2022-11-07T05:13:20.696519Z","shell.execute_reply":"2022-11-07T05:13:20.705417Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    cycle_gan_model = CycleGan(\n        monet_generator, photo_generator, 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":"2022-11-07T05:13:20.707285Z","iopub.execute_input":"2022-11-07T05:13:20.707627Z","iopub.status.idle":"2022-11-07T05:13:20.762213Z","shell.execute_reply.started":"2022-11-07T05:13:20.707584Z","shell.execute_reply":"2022-11-07T05:13:20.761272Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cycle_gan_model.fit(\n    tf.data.Dataset.zip((monet_ds, photo_ds)),\n    epochs=100\n)","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:13:20.763385Z","iopub.execute_input":"2022-11-07T05:13:20.763654Z","iopub.status.idle":"2022-11-07T05:15:42.599230Z","shell.execute_reply.started":"2022-11-07T05:13:20.763620Z","shell.execute_reply":"2022-11-07T05:15:42.598093Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"_, ax = plt.subplots(5, 2, figsize=(12, 12))\nfor i, img in enumerate(photo_ds.take(5)):\n    prediction = monet_generator(img, training=False)[0].numpy()\n    prediction = (prediction * 127.5 + 127.5).astype(np.uint8)\n    img = (img[0] * 127.5 + 127.5).numpy().astype(np.uint8)\n    \n    ax[i, 0].imshow(img)\n    ax[i, 1].imshow(prediction)\n    ax[i, 0].set_title(\"Input Photo\")\n    ax[i, 1].set_title(\"Monet-esque\")\n    ax[i, 0].axis(\"off\")\n    ax[i, 1].axis(\"off\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:15:42.600920Z","iopub.execute_input":"2022-11-07T05:15:42.601245Z","iopub.status.idle":"2022-11-07T05:15:44.876032Z","shell.execute_reply.started":"2022-11-07T05:15:42.601204Z","shell.execute_reply":"2022-11-07T05:15:44.875239Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import PIL\n! mkdir ../images","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:15:44.877072Z","iopub.execute_input":"2022-11-07T05:15:44.877486Z","iopub.status.idle":"2022-11-07T05:15:46.019428Z","shell.execute_reply.started":"2022-11-07T05:15:44.877451Z","shell.execute_reply":"2022-11-07T05:15:46.018119Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"i = 1\nfor img in photo_ds:\n    prediction = monet_generator(img, training=False)[0].numpy()\n    prediction = (prediction * 127.5 + 127.5).astype(np.uint8)\n    im = PIL.Image.fromarray(prediction)\n    im.save(\"../images/\" + str(i) + \".jpg\")\n    i += 1","metadata":{"execution":{"iopub.status.busy":"2022-11-07T05:15:46.022004Z","iopub.execute_input":"2022-11-07T05:15:46.022403Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import shutil\nshutil.make_archive(\"/kaggle/working/images\", \"zip\", \"/kaggle/images\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}