{"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":"## Second Commit","metadata":{"execution":{"iopub.status.busy":"2023-02-21T16:19:49.105263Z","iopub.execute_input":"2023-02-21T16:19:49.106113Z","iopub.status.idle":"2023-02-21T16:20:15.130169Z","shell.execute_reply.started":"2023-02-21T16:19:49.106077Z","shell.execute_reply":"2023-02-21T16:20:15.129135Z"}}},{"cell_type":"markdown","source":"##  This notebook utilizes a CycleGAN architecture to add Monet-style to photos. Import the following packages and change the accelerator to TPU.","metadata":{}},{"cell_type":"markdown","source":"## Cycle GAN Model 2","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\n!pip install tensorflow_addons\nimport tensorflow_addons as tfa\nfrom kaggle_datasets import KaggleDatasets as KD\nimport matplotlib.pyplot as plt\nimport numpy as np\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)\nautoTone = tf.data.experimental.AUTOTUNE   \nprint(tf.__version__)","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:11:32.220903Z","iopub.execute_input":"2023-02-22T16:11:32.222099Z","iopub.status.idle":"2023-02-22T16:11:48.492250Z","shell.execute_reply.started":"2023-02-22T16:11:32.221997Z","shell.execute_reply":"2023-02-22T16:11:48.491005Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Make the 'Accelerator' 'tpu' from the 'Setting' section","metadata":{}},{"cell_type":"code","source":"gcsPath = KD().get_gcs_path()","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:18.329541Z","iopub.execute_input":"2023-02-22T16:12:18.330504Z","iopub.status.idle":"2023-02-22T16:12:18.770720Z","shell.execute_reply.started":"2023-02-22T16:12:18.330467Z","shell.execute_reply":"2023-02-22T16:12:18.769786Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Load datasets ","metadata":{}},{"cell_type":"code","source":"photoFilenames = tf.io.gfile.glob(str(gcsPath + '/photo_tfrec/*.tfrec'))\nprint('Photo tfRecord Files:', len(photoFilenames))\nmonetFilenames = tf.io.gfile.glob(str(gcsPath + '/monet_tfrec/*.tfrec'))\nprint('Monet tfRecord Files:', len(monetFilenames))","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:20.029460Z","iopub.execute_input":"2023-02-22T16:12:20.030157Z","iopub.status.idle":"2023-02-22T16:12:20.606594Z","shell.execute_reply.started":"2023-02-22T16:12:20.030114Z","shell.execute_reply":"2023-02-22T16:12:20.605518Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## These images are RGB images so channel = 3. \n## *Scaling the images to a [-1, 1] scale. We don't need the labels or the image id so we'll only return the image from the tfrecord*","metadata":{}},{"cell_type":"code","source":"imgSize = [256, 256]\n\ndef decode_image(img):\n    img = tf.image.decode_jpeg(img, channels=3)\n    img = (tf.cast(img, tf.float32) / 127.5) - 1\n    img = tf.reshape(img, [*imgSize, 3])\n    return img\n\ndef read_tfrecord(exm):\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    exm = tf.io.parse_single_example(exm, tfrecord_format)\n    img = decode_image(exm['image'])\n    return img","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:25.281346Z","iopub.execute_input":"2023-02-22T16:12:25.281699Z","iopub.status.idle":"2023-02-22T16:12:25.289689Z","shell.execute_reply.started":"2023-02-22T16:12:25.281668Z","shell.execute_reply":"2023-02-22T16:12:25.288582Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## *Using above function, extracting images*","metadata":{}},{"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=autoTone)\n    return dataset","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:27.089271Z","iopub.execute_input":"2023-02-22T16:12:27.090293Z","iopub.status.idle":"2023-02-22T16:12:27.096239Z","shell.execute_reply.started":"2023-02-22T16:12:27.090256Z","shell.execute_reply":"2023-02-22T16:12:27.094998Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Loading dataset from path","metadata":{}},{"cell_type":"code","source":"monetDs = load_dataset(monetFilenames, labeled=True).batch(1)\nphotoDs = load_dataset(photoFilenames, labeled=True).batch(1)\nexmMonet = next(iter(monetDs))\nexmPhoto = next(iter(photoDs))","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:28.167018Z","iopub.execute_input":"2023-02-22T16:12:28.167764Z","iopub.status.idle":"2023-02-22T16:12:32.689735Z","shell.execute_reply.started":"2023-02-22T16:12:28.167722Z","shell.execute_reply":"2023-02-22T16:12:32.688765Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## *Examples*","metadata":{}},{"cell_type":"code","source":"plt.subplot(121)\nplt.title('Photo')\nplt.imshow(exmPhoto[0] * 0.5 + 0.5)\n\nplt.subplot(122)\nplt.title('Monet')\nplt.imshow(exmMonet[0] * 0.5 + 0.5)","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:36.133190Z","iopub.execute_input":"2023-02-22T16:12:36.133546Z","iopub.status.idle":"2023-02-22T16:12:36.454854Z","shell.execute_reply.started":"2023-02-22T16:12:36.133516Z","shell.execute_reply":"2023-02-22T16:12:36.453882Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Generator","metadata":{}},{"cell_type":"code","source":"outputChannels = 3\n\ndef downsample(filters, size, apply_instancenorm=True):\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gammaInit = 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=gammaInit))\n\n    result.add(layers.LeakyReLU())\n\n    return result","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:38.196620Z","iopub.execute_input":"2023-02-22T16:12:38.196962Z","iopub.status.idle":"2023-02-22T16:12:38.204175Z","shell.execute_reply.started":"2023-02-22T16:12:38.196932Z","shell.execute_reply":"2023-02-22T16:12:38.203236Z"},"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    gammaInit = keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n\n    result = keras.Sequential()\n    result.add(layers.Conv2DTranspose(filters, size, strides=2,\n                                      padding='same',\n                                      kernel_initializer=initializer,\n                                      use_bias=False))\n\n    result.add(tfa.layers.InstanceNormalization(gamma_initializer=gammaInit))\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":"2023-02-22T16:12:38.856372Z","iopub.execute_input":"2023-02-22T16:12:38.856771Z","iopub.status.idle":"2023-02-22T16:12:38.865063Z","shell.execute_reply.started":"2023-02-22T16:12:38.856736Z","shell.execute_reply":"2023-02-22T16:12:38.863021Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def Generator():\n    inputs = layers.Input(shape=[256,256,3])\n    downStack = [\n        downsample(64, 4, apply_instancenorm=False),\n        downsample(128, 4), \n        downsample(256, 4), \n        downsample(512, 4), \n        downsample(512, 4), \n        downsample(512, 4), \n        downsample(512, 4), \n        downsample(512, 4), \n    ]\n\n    upStack = [\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(outputChannels, 4,\n                                  strides=2,\n                                  padding='same',\n                                  kernel_initializer=initializer,\n                                  activation='tanh')\n\n    x = inputs\n    \n    skips = []\n    \n    for down in downStack:\n        x = down(x)\n        skips.append(x)\n\n    skips = reversed(skips[:-1])\n    for up, skip in zip(upStack, 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":"2023-02-22T16:12:39.310755Z","iopub.execute_input":"2023-02-22T16:12:39.311067Z","iopub.status.idle":"2023-02-22T16:12:39.320866Z","shell.execute_reply.started":"2023-02-22T16:12:39.311039Z","shell.execute_reply":"2023-02-22T16:12:39.319646Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Discriminator","metadata":{}},{"cell_type":"code","source":"def Discriminator():\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gammaInit = 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) \n    down2 = downsample(128, 4)(down1)\n    down3 = downsample(256, 4)(down2)\n\n    zeroPad1 = layers.ZeroPadding2D()(down3) \n    conv = layers.Conv2D(512, 4, strides=1,\n                         kernel_initializer=initializer,\n                         use_bias=False)(zeroPad1) \n\n    norm1 = tfa.layers.InstanceNormalization(gamma_initializer=gammaInit)(conv)\n\n    leakyRelu = layers.LeakyReLU()(norm1)\n\n    zeroPad2 = layers.ZeroPadding2D()(leakyRelu) \n\n    last = layers.Conv2D(1, 4, strides=1,\n                         kernel_initializer=initializer)(zeroPad2) \n\n    return tf.keras.Model(inputs=inp, outputs=last)","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:40.237535Z","iopub.execute_input":"2023-02-22T16:12:40.237891Z","iopub.status.idle":"2023-02-22T16:12:40.246070Z","shell.execute_reply.started":"2023-02-22T16:12:40.237860Z","shell.execute_reply":"2023-02-22T16:12:40.245119Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Making generator and discriminator callable ","metadata":{}},{"cell_type":"code","source":"with strategy.scope():\n    monetGenerator = Generator() \n    photoGenerator = Generator() \n\n    monetDiscriminator = Discriminator() \n    photoDiscriminator = Discriminator()","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:41.108235Z","iopub.execute_input":"2023-02-22T16:12:41.108588Z","iopub.status.idle":"2023-02-22T16:12:43.429758Z","shell.execute_reply.started":"2023-02-22T16:12:41.108557Z","shell.execute_reply":"2023-02-22T16:12:43.428801Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Output of untrained generator","metadata":{}},{"cell_type":"code","source":"toMonet = monetGenerator(exmPhoto)\n\nplt.subplot(1, 2, 1)\nplt.title(\"Original Photo\")\nplt.imshow(exmPhoto[0] * 0.5 + 0.5)\n\nplt.subplot(1, 2, 2)\nplt.title(\"Monet-esque Photo\")\nplt.imshow(toMonet[0] * 0.5 + 0.5)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:43.431735Z","iopub.execute_input":"2023-02-22T16:12:43.432107Z","iopub.status.idle":"2023-02-22T16:12:50.643246Z","shell.execute_reply.started":"2023-02-22T16:12:43.432068Z","shell.execute_reply":"2023-02-22T16:12:50.642340Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## *CycleGAN model to train the generator against the discriminator together*","metadata":{}},{"cell_type":"code","source":"class CycleGan(keras.Model):\n    def __init__(\n        self,\n        monetGenerator,\n        photoGenerator,\n        monetDiscriminator,\n        photoDiscriminator,\n        lambda_cycle=10,\n    ):\n        super(CycleGan, self).__init__()\n        self.m_gen = monetGenerator\n        self.p_gen = photoGenerator\n        self.m_disc = monetDiscriminator\n        self.p_disc = photoDiscriminator\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\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\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":"2023-02-22T16:12:53.356918Z","iopub.execute_input":"2023-02-22T16:12:53.357362Z","iopub.status.idle":"2023-02-22T16:12:53.375292Z","shell.execute_reply.started":"2023-02-22T16:12:53.357329Z","shell.execute_reply":"2023-02-22T16:12:53.374021Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## *Loss Function*","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\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":"2023-02-22T16:12:54.451838Z","iopub.execute_input":"2023-02-22T16:12:54.452512Z","iopub.status.idle":"2023-02-22T16:12:54.458710Z","shell.execute_reply.started":"2023-02-22T16:12:54.452477Z","shell.execute_reply":"2023-02-22T16:12:54.457661Z"},"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":"2023-02-22T16:12:55.195128Z","iopub.execute_input":"2023-02-22T16:12:55.195935Z","iopub.status.idle":"2023-02-22T16:12:55.207641Z","shell.execute_reply.started":"2023-02-22T16:12:55.195886Z","shell.execute_reply":"2023-02-22T16:12:55.206633Z"},"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":"2023-02-22T16:12:56.094861Z","iopub.execute_input":"2023-02-22T16:12:56.095817Z","iopub.status.idle":"2023-02-22T16:12:56.101424Z","shell.execute_reply.started":"2023-02-22T16:12:56.095772Z","shell.execute_reply":"2023-02-22T16:12:56.100412Z"},"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":"2023-02-22T16:12:56.592654Z","iopub.execute_input":"2023-02-22T16:12:56.592970Z","iopub.status.idle":"2023-02-22T16:12:56.598046Z","shell.execute_reply.started":"2023-02-22T16:12:56.592940Z","shell.execute_reply":"2023-02-22T16:12:56.597040Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training the Cycle GAN Model","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\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":"2023-02-22T16:12:57.819857Z","iopub.execute_input":"2023-02-22T16:12:57.820540Z","iopub.status.idle":"2023-02-22T16:12:57.826867Z","shell.execute_reply.started":"2023-02-22T16:12:57.820505Z","shell.execute_reply":"2023-02-22T16:12:57.825707Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    cycle_gan_model = CycleGan(\n        monetGenerator, photoGenerator, monetDiscriminator, photoDiscriminator\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":"2023-02-22T16:12:58.663494Z","iopub.execute_input":"2023-02-22T16:12:58.664442Z","iopub.status.idle":"2023-02-22T16:12:58.684862Z","shell.execute_reply.started":"2023-02-22T16:12:58.664384Z","shell.execute_reply":"2023-02-22T16:12:58.684026Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cycle_gan_model.fit(\n    tf.data.Dataset.zip((monetDs, photoDs)),\n    epochs=30\n)","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:12:59.519259Z","iopub.execute_input":"2023-02-22T16:12:59.519896Z","iopub.status.idle":"2023-02-22T16:52:50.265898Z","shell.execute_reply.started":"2023-02-22T16:12:59.519862Z","shell.execute_reply":"2023-02-22T16:52:50.265017Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## *Visualizing Results*","metadata":{}},{"cell_type":"code","source":"_, ax = plt.subplots(5, 2, figsize=(14, 14))\nfor i, img in enumerate(photoDs.take(5)):\n    prediction = monetGenerator(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":"2023-02-22T16:52:50.267996Z","iopub.execute_input":"2023-02-22T16:52:50.268471Z","iopub.status.idle":"2023-02-22T16:52:51.661910Z","shell.execute_reply.started":"2023-02-22T16:52:50.268432Z","shell.execute_reply":"2023-02-22T16:52:51.661120Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import PIL\n! mkdir ../images","metadata":{"execution":{"iopub.status.busy":"2023-02-22T16:52:51.663376Z","iopub.execute_input":"2023-02-22T16:52:51.664042Z","iopub.status.idle":"2023-02-22T16:52:52.687885Z","shell.execute_reply.started":"2023-02-22T16:52:51.664006Z","shell.execute_reply":"2023-02-22T16:52:52.686424Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"i = 1\nfor img in photoDs:\n    prediction = monetGenerator(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":"2023-02-22T17:05:35.742546Z","iopub.execute_input":"2023-02-22T17:05:35.743118Z","iopub.status.idle":"2023-02-22T17:10:48.706524Z","shell.execute_reply.started":"2023-02-22T17:05:35.743071Z","shell.execute_reply":"2023-02-22T17:10:48.705513Z"},"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":"2023-02-22T17:10:48.708807Z","iopub.execute_input":"2023-02-22T17:10:48.709109Z","iopub.status.idle":"2023-02-22T17:10:52.833665Z","shell.execute_reply.started":"2023-02-22T17:10:48.709082Z","shell.execute_reply":"2023-02-22T17:10:52.832785Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}