{"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":"2022-06-29T10:02:40.819126Z","iopub.execute_input":"2022-06-29T10:02:40.820023Z","iopub.status.idle":"2022-06-29T10:02:47.677283Z","shell.execute_reply.started":"2022-06-29T10:02:40.819975Z","shell.execute_reply":"2022-06-29T10:02:47.676334Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Introduction and setup**","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\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":"2022-06-29T10:03:05.387749Z","iopub.execute_input":"2022-06-29T10:03:05.388096Z","iopub.status.idle":"2022-06-29T10:03:14.382331Z","shell.execute_reply.started":"2022-06-29T10:03:05.388064Z","shell.execute_reply":"2022-06-29T10:03:14.38001Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Load in the data**","metadata":{}},{"cell_type":"code","source":"GCS_PATH = KaggleDatasets().get_gcs_path()","metadata":{"execution":{"iopub.status.busy":"2022-06-29T10:03:21.360921Z","iopub.execute_input":"2022-06-29T10:03:21.361254Z","iopub.status.idle":"2022-06-29T10:03:21.750163Z","shell.execute_reply.started":"2022-06-29T10:03:21.361219Z","shell.execute_reply":"2022-06-29T10:03:21.749213Z"},"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":"2022-06-29T10:03:28.363224Z","iopub.execute_input":"2022-06-29T10:03:28.364393Z","iopub.status.idle":"2022-06-29T10:03:28.539642Z","shell.execute_reply.started":"2022-06-29T10:03:28.364337Z","shell.execute_reply":"2022-06-29T10:03:28.538722Z"},"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":"2022-06-29T10:03:34.600755Z","iopub.execute_input":"2022-06-29T10:03:34.601692Z","iopub.status.idle":"2022-06-29T10:03:34.609135Z","shell.execute_reply.started":"2022-06-29T10:03:34.60162Z","shell.execute_reply":"2022-06-29T10:03:34.608274Z"},"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":"2022-06-29T10:03:38.946589Z","iopub.execute_input":"2022-06-29T10:03:38.947112Z","iopub.status.idle":"2022-06-29T10:03:38.95214Z","shell.execute_reply.started":"2022-06-29T10:03:38.94708Z","shell.execute_reply":"2022-06-29T10:03:38.95116Z"},"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":"2022-06-29T10:03:41.749672Z","iopub.execute_input":"2022-06-29T10:03:41.749988Z","iopub.status.idle":"2022-06-29T10:03:41.951998Z","shell.execute_reply.started":"2022-06-29T10:03:41.749958Z","shell.execute_reply":"2022-06-29T10:03:41.95104Z"},"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":"2022-06-29T10:03:44.411072Z","iopub.execute_input":"2022-06-29T10:03:44.411448Z","iopub.status.idle":"2022-06-29T10:03:45.515101Z","shell.execute_reply.started":"2022-06-29T10:03:44.41141Z","shell.execute_reply":"2022-06-29T10:03:45.513963Z"},"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":"2022-06-29T10:03:48.59855Z","iopub.execute_input":"2022-06-29T10:03:48.5989Z","iopub.status.idle":"2022-06-29T10:03:49.023876Z","shell.execute_reply.started":"2022-06-29T10:03:48.598868Z","shell.execute_reply":"2022-06-29T10:03:49.022743Z"},"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', 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":"2022-06-29T10:03:55.882108Z","iopub.execute_input":"2022-06-29T10:03:55.883123Z","iopub.status.idle":"2022-06-29T10:03:55.889908Z","shell.execute_reply.started":"2022-06-29T10:03:55.883082Z","shell.execute_reply":"2022-06-29T10:03:55.888882Z"},"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        \n    result.add(layers.ReLU())\n    \n    return result","metadata":{"execution":{"iopub.status.busy":"2022-06-29T10:03:59.519446Z","iopub.execute_input":"2022-06-29T10:03:59.51996Z","iopub.status.idle":"2022-06-29T10:03:59.52689Z","shell.execute_reply.started":"2022-06-29T10:03:59.519929Z","shell.execute_reply":"2022-06-29T10:03:59.525889Z"},"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    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    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":"2022-06-29T10:07:38.966517Z","iopub.execute_input":"2022-06-29T10:07:38.967323Z","iopub.status.idle":"2022-06-29T10:07:38.979836Z","shell.execute_reply.started":"2022-06-29T10:07:38.967253Z","shell.execute_reply":"2022-06-29T10:07:38.979049Z"},"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":"2022-06-29T10:08:15.005622Z","iopub.execute_input":"2022-06-29T10:08:15.005951Z","iopub.status.idle":"2022-06-29T10:08:15.017363Z","shell.execute_reply.started":"2022-06-29T10:08:15.005919Z","shell.execute_reply":"2022-06-29T10:08:15.016163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    monet_generator = Generator() #transforms photos to Monet paintings\n    photo_generator = Generator() #transforms Monet to photo like\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":"2022-06-29T10:08:18.642129Z","iopub.execute_input":"2022-06-29T10:08:18.642946Z","iopub.status.idle":"2022-06-29T10:08:23.493651Z","shell.execute_reply.started":"2022-06-29T10:08:18.642887Z","shell.execute_reply":"2022-06-29T10:08:23.492674Z"},"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 Photo\")\nplt.imshow(to_monet[0]*0.5+0.5)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-06-29T10:08:27.227698Z","iopub.execute_input":"2022-06-29T10:08:27.228241Z","iopub.status.idle":"2022-06-29T10:08:28.724287Z","shell.execute_reply.started":"2022-06-29T10:08:27.228203Z","shell.execute_reply":"2022-06-29T10:08:28.723411Z"},"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            \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, self.m_gen.trainable_variables)\n        photo_generator_gradients = tape.gradient(total_photo_gen_loss, self.p_gen.trainable_variables)\n\n        monet_discriminator_gradients = tape.gradient(monet_disc_loss, self.m_disc.trainable_variables)\n        photo_discriminator_gradients = tape.gradient(photo_disc_loss, self.p_disc.trainable_variables)\n        \n        # Apply the gradients to the optimizer\n        self.m_gen_optimizer.apply_gradients(zip(monet_generator_gradients, self.m_gen.trainable_variables))\n        self.p_gen_optimizer.apply_gradients(zip(photo_generator_gradients, self.p_gen.trainable_variables))\n        self.m_disc_optimizer.apply_gradients(zip(monet_discriminator_gradients, self.m_disc.trainable_variables))\n        self.p_disc_optimizer.apply_gradients(zip(photo_discriminator_gradients, 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        }\n","metadata":{"execution":{"iopub.status.busy":"2022-06-29T10:17:26.245457Z","iopub.execute_input":"2022-06-29T10:17:26.245768Z","iopub.status.idle":"2022-06-29T10:17:26.265459Z","shell.execute_reply.started":"2022-06-29T10:17:26.245739Z","shell.execute_reply":"2022-06-29T10:17:26.264756Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Define loss functions**","metadata":{}},{"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        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":"2022-06-29T10:08:42.501047Z","iopub.execute_input":"2022-06-29T10:08:42.50219Z","iopub.status.idle":"2022-06-29T10:08:42.510385Z","shell.execute_reply.started":"2022-06-29T10:08:42.502142Z","shell.execute_reply":"2022-06-29T10:08:42.509067Z"},"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":"2022-06-29T10:08:56.166052Z","iopub.execute_input":"2022-06-29T10:08:56.166988Z","iopub.status.idle":"2022-06-29T10:08:56.172908Z","shell.execute_reply.started":"2022-06-29T10:08:56.166942Z","shell.execute_reply":"2022-06-29T10:08:56.171865Z"},"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))","metadata":{"execution":{"iopub.status.busy":"2022-06-29T10:17:20.545634Z","iopub.execute_input":"2022-06-29T10:17:20.546152Z","iopub.status.idle":"2022-06-29T10:17:20.552494Z","shell.execute_reply.started":"2022-06-29T10:17:20.5461Z","shell.execute_reply":"2022-06-29T10:17:20.551486Z"},"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":"2022-06-29T10:09:20.531599Z","iopub.execute_input":"2022-06-29T10:09:20.532209Z","iopub.status.idle":"2022-06-29T10:09:20.536802Z","shell.execute_reply.started":"2022-06-29T10:09:20.532176Z","shell.execute_reply":"2022-06-29T10:09:20.536208Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Train the CycleGAN**","metadata":{}},{"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":"2022-06-29T10:09:25.092912Z","iopub.execute_input":"2022-06-29T10:09:25.093212Z","iopub.status.idle":"2022-06-29T10:09:25.099883Z","shell.execute_reply.started":"2022-06-29T10:09:25.093182Z","shell.execute_reply":"2022-06-29T10:09:25.099266Z"},"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)","metadata":{"execution":{"iopub.status.busy":"2022-06-29T10:17:30.959268Z","iopub.execute_input":"2022-06-29T10:17:30.959681Z","iopub.status.idle":"2022-06-29T10:17:31.026818Z","shell.execute_reply.started":"2022-06-29T10:17:30.959653Z","shell.execute_reply":"2022-06-29T10:17:31.025854Z"},"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":"2022-06-29T10:18:45.29518Z","iopub.execute_input":"2022-06-29T10:18:45.295637Z","iopub.status.idle":"2022-06-29T10:18:51.171891Z","shell.execute_reply.started":"2022-06-29T10:18:45.295605Z","shell.execute_reply":"2022-06-29T10:18:51.170629Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Visualize Monet Photos**","metadata":{}},{"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\")\n    ax[i,0].axis(\"off\")\n    ax[i,1].axis(\"off\")\nplt.show()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Create submission file**","metadata":{}},{"cell_type":"code","source":"import PIL\n! mkdir ../images","metadata":{},"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_count":null,"outputs":[]},{"cell_type":"code","source":"import shutil\nshutil.make_archive(\"/kaggle/working/images\",'zip',\"/kaggle/images\")","metadata":{},"execution_count":null,"outputs":[]}]}