{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Resources\n* https://arxiv.org/abs/1511.06434\n* https://arxiv.org/abs/1606.03498\n* https://machinelearningmastery.com/how-to-train-stable-generative-adversarial-networks/\n* https://machinelearningmastery.com/rectified-linear-activation-function-for-deep-learning-neural-networks/"},{"metadata":{},"cell_type":"markdown","source":"# CHANGELOG\nV8:\n* Removing dropout in both discriminator and generator to see what happens\n* Adding minibatch discriminator\n\n\nv7:\n\n* Hopefully fixed the output being too small\n* Increased epochs from 25 to 30\n\nv6:\n\n* Change dropout from 0.5 to 0.2 to see what happens\n\nv5:\n\n* Undo switch to batch normalisation\n\nv4:\n\n* Add 50% dropout to downscaling to see what happens\n* Change instance normalisation to batch normalisation to see what happens\n\nv3:\n\nMade more changes in accordance with recommendations by [this paper](https://arxiv.org/abs/1511.06434)\n* Remove Dense layer just before output\n* Use ReLU instead of LeakyReLU for Generator\n* Use only a single layer to up/downscale\n\nv2:\n\n* Replace MaxPool2D with Conv2D with strides=2 as recommended by [this paper](https://arxiv.org/abs/1511.06434)\n\nv1:\n\n* Add random_jitter_and_flip for more noise to see what happens"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# Initial setup\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nimport tensorflow_addons as tfa\nimport tensorflow_datasets as tfds\n\nfrom kaggle_datasets import KaggleDatasets\nimport matplotlib.pyplot as plt\nimport numpy as np\n\nfrom functools import partial\nfrom albumentations import (\n    Compose, RandomBrightness, JpegCompression, HueSaturationValue, RandomContrast, HorizontalFlip,\n    Rotate\n)\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__)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Provided images are sized to `256 x 256`. RGB = 3 Channels. Need to scale the images to a `[-1, 1]` scale."},{"metadata":{"trusted":true},"cell_type":"code","source":"import re\n\nGCS_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))\n\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\nn_monet_samples = count_data_items(MONET_FILENAMES)\nn_photo_samples = count_data_items(PHOTO_FILENAMES)\n\nprint(f'Monet TFRecord files: {len(MONET_FILENAMES)}')\nprint(f'Monet image files: {n_monet_samples}')\nprint(f'Photo TFRecord files: {len(PHOTO_FILENAMES)}')\nprint(f'Photo image files: {n_photo_samples}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def normalize(image):\n    return (tf.cast(image, tf.float32) / 127.5) - 1\n\ndef decode_image(image):\n    image = tf.image.decode_jpeg(image, channels=3)\n    image = tf.reshape(image, [256, 256, 3])\n    return image\n\ndef random_crop(image):\n    cropped_image = tf.image.random_crop(image, size=[256, 256, 3])\n    return cropped_image\n\ndef random_jitter(image):\n    # resizing to 286 x 286 x 3 \n    image = tf.image.resize(image, [int(256*1.3), int(256*1.3)],\n                          method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)\n    # randomly cropping to 256 x 256 x 3\n    image = random_crop(image)\n    return image\n\ndef random_jitter_and_flip(image):\n    # resizing to 286 x 286 x 3 \n    image = tf.image.resize(image, [int(256*1.3), int(256*1.3)],\n                          method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)\n    # randomly cropping to 256 x 256 x 3\n    image = random_crop(image)\n    # random mirroring\n    image = random_flip(image)\n    return image\n\ndef random_flip(image):\n    return tf.image.flip_left_right(image)\n\ndef preprocess_image_train(image, label=None):\n    image = random_jitter(image)\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=False, ordered=False, repeats=200, noise=False):\n    dataset = tf.data.TFRecordDataset(filenames)\n    dataset = dataset.map(read_tfrecord, num_parallel_calls=AUTOTUNE);\n    if noise == True:\n        dataset = dataset.concatenate(dataset.map(random_jitter_and_flip, num_parallel_calls=AUTOTUNE).shuffle(10000))\n        dataset = dataset.concatenate(dataset.map(random_flip, num_parallel_calls=AUTOTUNE).shuffle(100000))\n        dataset = dataset.concatenate(dataset.map(random_jitter, num_parallel_calls=AUTOTUNE).shuffle(10000, reshuffle_each_iteration=True).repeat(repeats))\n    dataset = dataset.map(normalize, num_parallel_calls=AUTOTUNE).shuffle(10000)\n    return dataset","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"OUTPUT_CHANNELS = 3\nLATENT_DIM = 1024\n\ndef downsample(filters, size, apply_dropout=False, 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=1, padding='same',\n    #                         kernel_initializer=initializer, use_bias=False))\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.BatchNormalization(gamma_initializer=gamma_init))\n\n    if apply_dropout:\n        result.add(layers.Dropout(0.2))\n\n    result.add(layers.ReLU())\n\n    return result","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def upsample(filters, size, apply_dropout=False, 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.Conv2DTranspose(filters, size, strides=1,\n    #                                  padding='same',\n    #                                  kernel_initializer=initializer,\n    #                                  use_bias=False))\n    result.add(layers.Conv2DTranspose(filters, size, strides=2,\n                                      padding='same',\n                                      kernel_initializer=initializer,\n                                      use_bias=False))\n    \n    if apply_instancenorm:\n        #result.add(layers.BatchNormalization(gamma_initializer=gamma_init))\n        result.add(tfa.layers.InstanceNormalization(gamma_initializer=gamma_init))\n\n    if apply_dropout:\n        result.add(layers.Dropout(0.2))\n\n    result.add(layers.ReLU())\n\n    return result","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Hyperparameters"},{"metadata":{"trusted":true},"cell_type":"code","source":"EPOCHS = 30\n\nLR_G = 2e-4\nLR_D = 2e-4\nbeta_1 = .5\n\nreal_label = .9\nfake_label = 0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def CycleGenerator():\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=False), # (bs, 2, 2, 1024)\n        upsample(512, 4, apply_dropout=False), # (bs, 4, 4, 1024)\n        upsample(512, 4, apply_dropout=False), # (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, apply_instancenorm=False), # (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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":false,"_kg_hide-input":false},"cell_type":"markdown","source":"def CycleDiscriminator():\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, apply_dropout=False, apply_instancenorm=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    Leaky_relu1 = layers.LeakyReLU()(conv)\n    \n    BatchNormalisation = layers.BatchNormalization()(Leaky_relu1)\n    \n    mini_batch_dis = MinibatchDiscrimination(num_kernel = 512, dim_kernel=5,name=\"mbd\")(conv)\n    \n    dense = layers.Dense(512)(mini_batch_dis)\n\n    norm1 = tfa.layers.InstanceNormalization(gamma_initializer=gamma_init)(dense)\n\n    leaky_relu2 = layers.LeakyReLU()(norm1)\n\n    zero_pad2 = layers.ZeroPadding2D()(leaky_relu) # (bs, 33, 33, 512)\n        \n    last_conv = layers.Conv2D(1, 4, strides=1,\n                         kernel_initializer=initializer)(zero_pad2) # (bs, 30, 30, 1)\n\n    last_relu = layers.LeakyReLU(alpha=0.2)(last_conv)\n    last_pool = layers.Flatten()(last_relu)\n    #last = layers.Dense(1, activation='sigmoid')(last_pool)\n\n    return tf.keras.Model(inputs=inp, outputs=last_pool)"},{"metadata":{"trusted":true},"cell_type":"code","source":"def CycleDiscriminator():\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, apply_dropout=False, apply_instancenorm=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    leaky_relu1 = layers.LeakyReLU()(conv)\n    \n    batch_normalisation = layers.BatchNormalization()(leaky_relu1)\n    \n    flatten = layers.Flatten()(batch_normalisation)\n    \n    dense1 = layers.Dense(512)(flatten)\n    \n    leaky_relu2 = layers.LeakyReLU()(dense1)\n    \n    mini_batch_dis = MinibatchDiscrimination(num_kernel = 512, dim_kernel=5,name=\"mbd\")(leaky_relu2)\n    \n    dense2 = layers.Dense(512)(mini_batch_dis)\n    \n    leakyrelu3 = layers.LeakyReLU()(dense2)\n    \n    last_pool = layers.Dense(1, activation='sigmoid')(leakyrelu3)\n    #last = layers.Dense(1, activation='sigmoid')(last_pool)\n\n    return tf.keras.Model(inputs=inp, outputs=last_pool)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Creating a minibatch discriminator custom layer from https://github.com/garridoq/gan-guide/blob/master/Minibatch%20discrimination_layer%20after.ipynb"},{"metadata":{"trusted":true},"cell_type":"code","source":"class MinibatchDiscrimination(tf.keras.layers.Layer):\n\n    def __init__(self, num_kernel, dim_kernel,kernel_initializer='glorot_uniform', **kwargs):\n        self.num_kernel = num_kernel\n        self.dim_kernel = dim_kernel\n        self.kernel_initializer = kernel_initializer\n        super(MinibatchDiscrimination, self).__init__(**kwargs)\n\n    def build(self, input_shape):\n        # Create a trainable weight variable for this layer.\n        self.kernel = self.add_weight(name='kernel', \n                                      shape=(input_shape[1], self.num_kernel*self.dim_kernel),\n                                      initializer=self.kernel_initializer,\n                                      trainable=True)\n        super(MinibatchDiscrimination, self).build(input_shape)  # Be sure to call this at the end\n\n    def call(self, x):\n        activation = tf.matmul(x, self.kernel)\n        activation = tf.reshape(activation, shape=(-1, self.num_kernel, self.dim_kernel))\n        #Mi\n        tmp1 = tf.expand_dims(activation, 3)\n        #Mj\n        tmp2 = tf.transpose(activation, perm=[1, 2, 0])\n        tmp2 = tf.expand_dims(tmp2, 0)\n        \n        diff = tmp1 - tmp2\n        \n        l1 = tf.reduce_sum(tf.math.abs(diff), axis=2)\n        features = tf.reduce_sum(tf.math.exp(-l1), axis=2)\n        return tf.concat([x, features], axis=1)        \n        \n        \n    def compute_output_shape(self, input_shape):\n        return (input_shape[0], input_shape[1] + self.num_kernel)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    monet_cycle_generator = CycleGenerator() # transforms photos to Monet-esque paintings\n    photo_cycle_generator = CycleGenerator() # transforms Monet paintings to be more like photos\n\n    monet_cycle_discriminator = CycleDiscriminator() # differentiates real Monet paintings and generated Monet paintings\n    photo_cycle_discriminator = CycleDiscriminator() # differentiates real photos and generated photos","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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        real_label=.5\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        self.real_label = real_label\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        batch_size = tf.shape(real_photo)[0]\n        labels_real = tf.zeros((batch_size, 1)) + self.real_label\n        labels_real += 0.05 * tf.random.uniform(tf.shape(labels_real))        \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_real_monet, disc_fake_monet, labels_real)\n            photo_gen_loss = self.gen_loss_fn(disc_real_photo, disc_fake_photo, labels_real)\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, labels_real)\n            photo_disc_loss = self.disc_loss_fn(disc_real_photo, disc_fake_photo, labels_real)\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        }","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    def discriminator_loss(predictions_real, predictions_gen, labels_real):\n        return (tf.reduce_mean((predictions_gen  - tf.reduce_mean(predictions_real) + labels_real) ** 2) +\n                tf.reduce_mean((predictions_real - tf.reduce_mean(predictions_gen)  - labels_real) ** 2))/2\n    \n    def generator_loss(predictions_real, predictions_gen, labels_real):\n        return (tf.reduce_mean((predictions_real - tf.reduce_mean(predictions_gen)  + labels_real) ** 2) +\n                tf.reduce_mean((predictions_gen  - tf.reduce_mean(predictions_real) - labels_real) ** 2)) / 2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    monet_generator_optimizer = tf.keras.optimizers.Adam(LR_G, beta_1=0.5)\n    photo_generator_optimizer = tf.keras.optimizers.Adam(LR_G, beta_1=0.5)\n\n    monet_discriminator_optimizer = tf.keras.optimizers.Adam(LR_D, beta_1=0.5)\n    photo_discriminator_optimizer = tf.keras.optimizers.Adam(LR_D, beta_1=0.5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with strategy.scope():\n    cycle_gan_model = CycleGan(\n        monet_cycle_generator, photo_cycle_generator, monet_cycle_discriminator, photo_cycle_discriminator, real_label=0.66\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    )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"cycle_gan_model.fit(\n    tf.data.Dataset.zip((load_dataset(MONET_FILENAMES, labeled=True, repeats=50, noise=True).batch(100, drop_remainder=True), load_dataset(PHOTO_FILENAMES, labeled=True, repeats=2, noise=True).batch(100, drop_remainder=True))),\n    epochs=EPOCHS\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"_, ax = plt.subplots(2, 5, figsize=(25, 5))\nfor i, img in enumerate(load_dataset(PHOTO_FILENAMES, labeled=True, repeats=2, noise=True).batch(100, drop_remainder=True).take(5)):\n    prediction = monet_cycle_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[0, i].imshow(img)\n    ax[1, i].imshow(prediction)\n    ax[0, i].set_title(\"Input Photo\")\n    ax[1, i].set_title(\"Monet-esque\")\n    ax[0, i].axis(\"off\")\n    ax[1, i].axis(\"off\")\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import PIL\n! mkdir ../images","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"i = 1\nfor img in load_dataset(PHOTO_FILENAMES, labeled=True, repeats=1).batch(1):\n    prediction = monet_cycle_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\n    \nprint(i)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import shutil\nshutil.make_archive(\"/kaggle/working/images\", 'zip', \"/kaggle/images\")","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}