{"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":"import os\n!pip install tensorflow_addons\n!pip install kaggle","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"markdown","source":"Updates of versions - \nIn version 2 we changed the size of filters from 4x4 to 3x3.\nIn version 3 we added flatten and dense\nIn version 4 we added 2 layers to the generator.\nIn version 5 we added 2 layers to the generator and 1 to discriminator.\nIn version 6 we added batch normalization.","metadata":{}},{"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\nfrom tqdm import tqdm\nfrom random import random\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 Exception as e:\n    print(e)\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":"2021-07-24T16:18:23.639787Z","iopub.execute_input":"2021-07-24T16:18:23.640160Z","iopub.status.idle":"2021-07-24T16:18:23.652486Z","shell.execute_reply.started":"2021-07-24T16:18:23.640128Z","shell.execute_reply":"2021-07-24T16:18:23.651550Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GCS_PATH =  KaggleDatasets().get_gcs_path()\n\nMONET_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":"2021-07-24T16:18:23.661683Z","iopub.execute_input":"2021-07-24T16:18:23.661974Z","iopub.status.idle":"2021-07-24T16:18:26.510643Z","shell.execute_reply.started":"2021-07-24T16:18:23.661949Z","shell.execute_reply":"2021-07-24T16:18:26.509838Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMAGE_SIZE = [256, 256]\n\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\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\ndef augment_image(image):\n    flip_image = tf.image.random_flip_left_right(image)\n    return flip_image\n\ndef load_dataset(filenames, labeled=True, ordered=False, augment=False):\n    dataset = tf.data.TFRecordDataset(filenames)\n    dataset = dataset.map(read_tfrecord, num_parallel_calls=AUTOTUNE)\n    if augment:\n        dataset = dataset.map(augment_image, num_parallel_calls=AUTOTUNE)\n        dataset = dataset.repeat(count=2)\n    return dataset","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:18:26.513954Z","iopub.execute_input":"2021-07-24T16:18:26.514233Z","iopub.status.idle":"2021-07-24T16:18:26.525787Z","shell.execute_reply.started":"2021-07-24T16:18:26.514205Z","shell.execute_reply":"2021-07-24T16:18:26.524890Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"monet_ds = load_dataset(MONET_FILENAMES, labeled=True, augment=True).batch(1)\nphoto_ds = load_dataset(PHOTO_FILENAMES, labeled=True, augment=True).batch(1)\nphoto_ds_test = load_dataset(PHOTO_FILENAMES, labeled=True, augment=False).batch(1)","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:18:26.527825Z","iopub.execute_input":"2021-07-24T16:18:26.528195Z","iopub.status.idle":"2021-07-24T16:18:26.662430Z","shell.execute_reply.started":"2021-07-24T16:18:26.528155Z","shell.execute_reply":"2021-07-24T16:18:26.661614Z"},"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":"2021-07-24T16:18:26.664058Z","iopub.execute_input":"2021-07-24T16:18:26.664382Z","iopub.status.idle":"2021-07-24T16:18:27.339436Z","shell.execute_reply.started":"2021-07-24T16:18:26.664348Z","shell.execute_reply":"2021-07-24T16:18:27.338564Z"},"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":"2021-07-24T16:18:27.340788Z","iopub.execute_input":"2021-07-24T16:18:27.341115Z","iopub.status.idle":"2021-07-24T16:18:27.802728Z","shell.execute_reply.started":"2021-07-24T16:18:27.341080Z","shell.execute_reply":"2021-07-24T16:18:27.801935Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def Generator():\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gamma_init = keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n    model = keras.Sequential()\n    model.add(layers.Conv2D(64,3,strides=2, padding='same', kernel_initializer=initializer, activation='relu', input_shape=[256,256,3]))\n    model.add(layers.BatchNormalization(gamma_initializer=gamma_init))\n    model.add(layers.Conv2D(128,3,strides=2, padding='same', kernel_initializer=initializer, activation='relu',use_bias=True))\n    model.add(layers.Conv2D(256,3,strides=2, padding='same', kernel_initializer=initializer, activation='relu',use_bias=True))\n    model.add(layers.Conv2D(512,3,strides=2, padding='same', kernel_initializer=initializer, activation='relu',use_bias=True))\n    model.add(layers.Conv2D(1024,3,strides=2, padding='same', kernel_initializer=initializer, activation='relu',use_bias=True))\n    model.add(layers.Conv2DTranspose(512,3,strides=2, padding='same', kernel_initializer=initializer, activation='relu',use_bias=True))\n    model.add(layers.BatchNormalization(gamma_initializer=gamma_init))\n    model.add(layers.Conv2DTranspose(256, 3, strides=2,padding='same', kernel_initializer=initializer, activation='relu', use_bias=True))   \n    model.add(layers.Conv2DTranspose(128, 3, strides=2,padding='same', kernel_initializer=initializer, activation='relu', use_bias=True))    \n    model.add(layers.Conv2DTranspose( 64, 3, strides=2,padding='same', kernel_initializer=initializer, activation='relu', use_bias=True))\n    model.add(layers.Conv2DTranspose(  3, 3, strides=2,padding='same', kernel_initializer=initializer, activation='tanh', use_bias=True))          \n    return model","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:18:27.804252Z","iopub.execute_input":"2021-07-24T16:18:27.804640Z","iopub.status.idle":"2021-07-24T16:18:27.818291Z","shell.execute_reply.started":"2021-07-24T16:18:27.804602Z","shell.execute_reply":"2021-07-24T16:18:27.816964Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def Discriminator(notarget=True):\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gamma_init = keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n    model = keras.Sequential()\n    model.add(layers.Conv2D(64,3,strides=2, padding='same', kernel_initializer=initializer, activation='relu', input_shape=[256,256,3]))\n    model.add(layers.BatchNormalization(gamma_initializer=gamma_init))\n    model.add(layers.Conv2D(128,3,strides=2, padding='same', kernel_initializer=initializer, activation='relu',use_bias=True))\n    model.add(layers.Conv2D(256,3,strides=2, padding='same', kernel_initializer=initializer, activation='relu',use_bias=True))\n    model.add(layers.Conv2D(512,3,strides=2, padding='same', kernel_initializer=initializer, activation='relu',use_bias=True))\n    model.add(layers.Conv2D(1,3,strides=1, padding='valid', kernel_initializer=initializer, activation='relu',use_bias=True))\n    return model","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:18:27.819991Z","iopub.execute_input":"2021-07-24T16:18:27.820435Z","iopub.status.idle":"2021-07-24T16:18:27.832330Z","shell.execute_reply.started":"2021-07-24T16:18:27.820393Z","shell.execute_reply":"2021-07-24T16:18:27.831136Z"},"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":"2021-07-24T16:18:27.836578Z","iopub.execute_input":"2021-07-24T16:18:27.837139Z","iopub.status.idle":"2021-07-24T16:18:28.182717Z","shell.execute_reply.started":"2021-07-24T16:18:27.837089Z","shell.execute_reply":"2021-07-24T16:18:28.181831Z"},"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":"2021-07-24T16:18:28.185414Z","iopub.execute_input":"2021-07-24T16:18:28.185974Z","iopub.status.idle":"2021-07-24T16:18:28.420651Z","shell.execute_reply.started":"2021-07-24T16:18:28.185934Z","shell.execute_reply":"2021-07-24T16:18:28.419657Z"},"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            # 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            # 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        # 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":"2021-07-24T16:18:28.422225Z","iopub.execute_input":"2021-07-24T16:18:28.422578Z","iopub.status.idle":"2021-07-24T16:18:28.440401Z","shell.execute_reply.started":"2021-07-24T16:18:28.422539Z","shell.execute_reply":"2021-07-24T16:18:28.439170Z"},"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, reduction=tf.keras.losses.Reduction.NONE)(tf.ones_like(real), real)\n\n        generated_loss = tf.keras.losses.BinaryCrossentropy(from_logits=True, reduction=tf.keras.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","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:18:28.442011Z","iopub.execute_input":"2021-07-24T16:18:28.442434Z","iopub.status.idle":"2021-07-24T16:18:28.453505Z","shell.execute_reply.started":"2021-07-24T16:18:28.442392Z","shell.execute_reply":"2021-07-24T16:18:28.452493Z"},"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, reduction=tf.keras.losses.Reduction.NONE)(tf.ones_like(generated), generated)","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:18:28.455072Z","iopub.execute_input":"2021-07-24T16:18:28.455500Z","iopub.status.idle":"2021-07-24T16:18:28.463308Z","shell.execute_reply.started":"2021-07-24T16:18:28.455460Z","shell.execute_reply":"2021-07-24T16:18:28.462461Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"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","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:18:28.465022Z","iopub.execute_input":"2021-07-24T16:18:28.465426Z","iopub.status.idle":"2021-07-24T16:18:28.472672Z","shell.execute_reply.started":"2021-07-24T16:18:28.465388Z","shell.execute_reply":"2021-07-24T16:18:28.471490Z"},"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":"2021-07-24T16:18:28.474306Z","iopub.execute_input":"2021-07-24T16:18:28.474805Z","iopub.status.idle":"2021-07-24T16:18:28.482441Z","shell.execute_reply.started":"2021-07-24T16:18:28.474749Z","shell.execute_reply":"2021-07-24T16:18:28.481642Z"},"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":"2021-07-24T16:18:28.483533Z","iopub.execute_input":"2021-07-24T16:18:28.483985Z","iopub.status.idle":"2021-07-24T16:18:28.491607Z","shell.execute_reply.started":"2021-07-24T16:18:28.483960Z","shell.execute_reply":"2021-07-24T16:18:28.490835Z"},"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":"2021-07-24T16:18:28.493124Z","iopub.execute_input":"2021-07-24T16:18:28.493461Z","iopub.status.idle":"2021-07-24T16:18:28.511923Z","shell.execute_reply.started":"2021-07-24T16:18:28.493426Z","shell.execute_reply":"2021-07-24T16:18:28.511185Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cycle_gan_model.m_disc.summary()","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:18:28.513068Z","iopub.execute_input":"2021-07-24T16:18:28.513391Z","iopub.status.idle":"2021-07-24T16:18:28.522465Z","shell.execute_reply.started":"2021-07-24T16:18:28.513359Z","shell.execute_reply":"2021-07-24T16:18:28.521417Z"},"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=25\n)","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:18:28.523799Z","iopub.execute_input":"2021-07-24T16:18:28.524312Z","iopub.status.idle":"2021-07-24T16:42:28.930684Z","shell.execute_reply.started":"2021-07-24T16:18:28.524278Z","shell.execute_reply":"2021-07-24T16:42:28.929724Z"},"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":"2021-07-24T16:42:28.932139Z","iopub.execute_input":"2021-07-24T16:42:28.932641Z","iopub.status.idle":"2021-07-24T16:42:29.880731Z","shell.execute_reply.started":"2021-07-24T16:42:28.932604Z","shell.execute_reply":"2021-07-24T16:42:29.879690Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import PIL\n! mkdir ../images","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:42:29.882260Z","iopub.execute_input":"2021-07-24T16:42:29.882590Z","iopub.status.idle":"2021-07-24T16:42:30.579135Z","shell.execute_reply.started":"2021-07-24T16:42:29.882557Z","shell.execute_reply":"2021-07-24T16:42:30.578036Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"i = 1\nfor img in photo_ds.take(7039):\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":"2021-07-24T16:42:30.580735Z","iopub.execute_input":"2021-07-24T16:42:30.581086Z","iopub.status.idle":"2021-07-24T16:43:58.533916Z","shell.execute_reply.started":"2021-07-24T16:42:30.581056Z","shell.execute_reply":"2021-07-24T16:43:58.532977Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import shutil\nshutil.make_archive(\"/kaggle/working/images\", 'zip', \"/kaggle/images\")","metadata":{"execution":{"iopub.status.busy":"2021-07-24T16:43:58.535908Z","iopub.execute_input":"2021-07-24T16:43:58.536327Z","iopub.status.idle":"2021-07-24T16:44:00.296548Z","shell.execute_reply.started":"2021-07-24T16:43:58.536288Z","shell.execute_reply":"2021-07-24T16:44:00.295624Z"},"trusted":true},"execution_count":null,"outputs":[]}]}