{"cells":[{"metadata":{},"cell_type":"markdown","source":"## Dependencies"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"#import libs\nimport os, random, json, PIL, shutil, re\nimport numpy as np\nimport pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nfrom kaggle_datasets import KaggleDatasets\nimport tensorflow as tf\nimport tensorflow.keras.layers as L\nimport tensorflow_addons as tfa\nfrom tensorflow.keras import Model, losses, optimizers","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## TPU configuration"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"try:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    print(f'Running on TPU {tpu.master()}')\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    strategy = tf.distribute.get_strategy()\n\n\nREPLICAS = strategy.num_replicas_in_sync\nprint(f'REPLICAS: {REPLICAS}')\nAUTO = tf.data.experimental.AUTOTUNE","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":false,"trusted":true},"cell_type":"code","source":"#Model parameters\nHEIGHT = 256\nWIDTH = 256\nCHANNELS = 3\nEPOCHS = 50\nBATCH_SIZE = 1","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Load data"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"GCS_PATH = KaggleDatasets().get_gcs_path('monet-gan-getting-started')\n\nMONET_FILENAMES = tf.io.gfile.glob(str(GCS_PATH + '/monet_tfrec/*.tfrec'))\nPHOTO_FILENAMES = tf.io.gfile.glob(str(GCS_PATH + '/photo_tfrec/*.tfrec'))\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":{},"cell_type":"markdown","source":"## Auxiliar functions"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"def decode_image(image):\n    image = tf.image.decode_jpeg(image, channels=CHANNELS)\n    image = (tf.cast(image, tf.float32) / 127.5) - 1\n    image = tf.reshape(image, [HEIGHT, WIDTH, CHANNELS])\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):\n    dataset = tf.data.TFRecordDataset(filenames)\n    dataset = dataset.map(read_tfrecord, num_parallel_calls=AUTO)\n    return dataset\n\ndef get_gan_dataset(monet_files, photo_files, augment=None, repeat=True, shuffle=True, batch_size=1):\n\n    monet_ds = load_dataset(monet_files)\n    photo_ds = load_dataset(photo_files)\n\n    if repeat:\n        monet_ds = monet_ds.repeat()\n        photo_ds = photo_ds.repeat()\n    if shuffle:\n        monet_ds = monet_ds.shuffle(2048)\n        photo_ds = photo_ds.shuffle(2048)\n        \n    monet_ds = monet_ds.batch(batch_size, drop_remainder=True)\n    photo_ds = photo_ds.batch(batch_size, drop_remainder=True)\n    monet_ds = monet_ds.cache()\n    photo_ds = photo_ds.cache()\n    monet_ds = monet_ds.prefetch(AUTO)\n    photo_ds = photo_ds.prefetch(AUTO)\n    \n    gan_ds = tf.data.Dataset.zip((monet_ds, photo_ds))\n    \n    return gan_ds\n\ndef display_samples(ds, row, col):\n    ds_iter = iter(ds)\n    plt.figure(figsize=(15, int(15*row/col)))\n    for j in range(row*col):\n        example_sample = next(ds_iter)\n        plt.subplot(row,col,j+1)\n        plt.axis('off')\n        plt.imshow(example_sample[0] * 0.5 + 0.5)\n    plt.show()\n        \ndef display_generated_samples(ds, model, n_samples):\n    ds_iter = iter(ds)\n    for n_sample in range(n_samples):\n        example_sample = next(ds_iter)\n        generated_sample = model.predict(example_sample)\n        \n        plt.subplot(121)\n        plt.title(\"input image\")\n        plt.imshow(example_sample[0] * 0.5 + 0.5)\n        plt.axis('off')\n        \n        plt.subplot(122)\n        plt.title(\"Generated image\")\n        plt.imshow(generated_sample[0] * 0.5 + 0.5)\n        plt.axis('off')\n        plt.show()\n        \ndef predict_and_save(input_ds, generator_model, output_path):\n    i = 1\n    for img in input_ds:\n        prediction = generator_model(img, training=False)[0].numpy() # make predition\n        prediction = (prediction * 127.5 + 127.5).astype(np.uint8)   # re-scale\n        im = PIL.Image.fromarray(prediction)\n        im.save(f'{output_path}{str(i)}.jpg')\n        i += 1\n                \n\n# Model functions\ndef downsample(filters, size, apply_instancenorm=True, strides=2):\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gamma_init = tf.keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n\n    result = tf.keras.Sequential()\n    result.add(L.Conv2D(filters, size, strides=strides, 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\n    result.add(L.LeakyReLU())\n\n    return result\n\ndef upsample(filters, size, apply_dropout=False, strides=2):\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gamma_init = tf.keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n\n    result = tf.keras.Sequential()\n    result.add(L.Conv2DTranspose(filters, size, strides=strides, padding='same',\n                                 kernel_initializer=initializer, use_bias=False))\n\n    result.add(tfa.layers.InstanceNormalization(gamma_initializer=gamma_init))\n\n    if apply_dropout:\n        result.add(L.Dropout(0.5))\n\n    result.add(L.ReLU())\n\n    return result","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Looking at a few Monet paintings"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"display_samples(load_dataset(MONET_FILENAMES).batch(1), 4, 6)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Looking at a few photo samples"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"display_samples(load_dataset(PHOTO_FILENAMES).batch(1), 4, 6)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Generator model"},{"metadata":{"trusted":true,"_kg_hide-input":false},"cell_type":"code","source":"OUTPUT_CHANNELS = 3\n\ndef generator_fn():\n    inputs = L.Input(shape=[HEIGHT, WIDTH, CHANNELS])\n\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 = L.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 = L.Concatenate()([x, skip])\n\n    x = last(x)\n\n    return Model(inputs=inputs, outputs=x)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Discriminator model"},{"metadata":{"trusted":true,"_kg_hide-input":false},"cell_type":"code","source":"def discriminator_fn():\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gamma_init = tf.keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n\n    inp = L.Input(shape=[HEIGHT, WIDTH, CHANNELS], 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 = L.ZeroPadding2D()(down3) # (bs, 34, 34, 256)\n    conv = L.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 = L.LeakyReLU()(norm1)\n\n    zero_pad2 = L.ZeroPadding2D()(leaky_relu) # (bs, 33, 33, 512)\n\n    last = L.Conv2D(1, 4, strides=1,\n                    kernel_initializer=initializer)(zero_pad2) # (bs, 30, 30, 1)\n\n    return Model(inputs=inp, outputs=last)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Build model (CycleGAN)"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"with strategy.scope():\n    monet_generator = generator_fn() # transforms photos to Monet-esque paintings\n    photo_generator = generator_fn() # transforms Monet paintings to be more like photos\n\n    monet_discriminator = discriminator_fn() # differentiates real Monet paintings and generated Monet paintings\n    photo_discriminator = discriminator_fn() # differentiates real photos and generated photos\n\n\nclass CycleGan(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\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        }","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Loss functions"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"with strategy.scope():\n    # Discriminator loss {0: fake, 1: real} (The discriminator loss outputs the average of the real and generated loss)\n    def discriminator_loss(real, generated):\n        real_loss = losses.BinaryCrossentropy(from_logits=True, reduction=losses.Reduction.NONE)(tf.ones_like(real), real)\n\n        generated_loss = losses.BinaryCrossentropy(from_logits=True, reduction=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\n    \n    # Generator loss\n    def generator_loss(generated):\n        return losses.BinaryCrossentropy(from_logits=True, reduction=losses.Reduction.NONE)(tf.ones_like(generated), generated)\n    \n    \n    # Cycle consistency loss (measures if original photo and the twice transformed photo to be similar to one another)\n    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\n\n    # Identity loss (compares the image with its generator (i.e. photo with photo generator))\n    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":{},"cell_type":"markdown","source":"# Train"},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"with strategy.scope():\n    # Create generators\n    monet_generator_optimizer = optimizers.Adam(2e-4, beta_1=0.5)\n    photo_generator_optimizer = optimizers.Adam(2e-4, beta_1=0.5)\n\n    # Create discriminators\n    monet_discriminator_optimizer = optimizers.Adam(2e-4, beta_1=0.5)\n    photo_discriminator_optimizer = optimizers.Adam(2e-4, beta_1=0.5)\n    \n    # Create GAN\n    gan_model = CycleGan(monet_generator, photo_generator, \n                         monet_discriminator, photo_discriminator)\n\n    gan_model.compile(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    \n\nhistory = gan_model.fit(get_gan_dataset(MONET_FILENAMES, PHOTO_FILENAMES, batch_size=BATCH_SIZE), \n                        steps_per_epoch=(n_monet_samples//BATCH_SIZE),\n                        epochs=EPOCHS,\n                        verbose=2).history","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Visualize predictions"},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"display_generated_samples(load_dataset(PHOTO_FILENAMES).batch(1), monet_generator, 7)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Make predictions"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"os.makedirs('../images/') # Create folder to save generated images\n\npredict_and_save(load_dataset(PHOTO_FILENAMES).batch(1), monet_generator, '../images/')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Submission file"},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"shutil.make_archive('/kaggle/working/images/', 'zip', '../images')\n\nprint(f\"Generated samples: {len([name for name in os.listdir('../images/') if os.path.isfile(os.path.join('../images/', name))])}\")","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}