{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"> ### Import libraries","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nimport tensorflow_addons as tfa\nfrom kaggle_datasets import KaggleDatasets\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport re\nimport PIL\nimport os\nimport shutil","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Configure TPU","metadata":{}},{"cell_type":"code","source":"try:\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\nAUTO = tf.data.experimental.AUTOTUNE\nprint(tf.__version__)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Get image data from google cloud storage","metadata":{}},{"cell_type":"code","source":"# Google Cloud Storage path for dataset\nGCS_PATH = KaggleDatasets().get_gcs_path('gan-getting-started')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Size of input data\nMONET_FILES = tf.io.gfile.glob(str(GCS_PATH + '/monet_tfrec/*.tfrec'))\nPHOTO_FILES = tf.io.gfile.glob(str(GCS_PATH + '/photo_tfrec/*.tfrec'))\n\nn = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in MONET_FILES]\nn_monet = np.sum(n)\nn = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in PHOTO_FILES]\nn_photo = np.sum(n)\n\nprint(f'Monet image files: {n_monet}')\nprint(f'Photo image files: {n_photo}')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Function to read image (tensorflow record)","metadata":{}},{"cell_type":"code","source":"def read_tfrecord(example):# read image\n    IMAGE_SIZE = [256, 256]\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    im = example['image']\n    \n    image = tf.image.decode_jpeg(im, channels=3)\n    image = (tf.cast(image, tf.float32) / 127.5) - 1\n    image = tf.reshape(image, [*IMAGE_SIZE, 3])\n    \n    return image","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Input image data augmentation","metadata":{}},{"cell_type":"code","source":"def augment_image(image): # input data augmentation\n    x = tf.random.uniform([], 0, 1.0, dtype=tf.float32)\n    y = tf.random.uniform([], 0, 1.0, dtype=tf.float32)\n    \n    if y > .5: # random crop image\n        image = tf.image.resize(image, [286, 286])\n        image = tf.image.random_crop(image, size=[256, 256, 3])\n            \n    if x > .6: # random flip image\n        image = tf.image.random_flip_left_right(image)\n    \n    return image","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Load Dataset","metadata":{}},{"cell_type":"code","source":"# Function to load dataset\ndef load_data(filenames):\n    dataset = tf.data.TFRecordDataset(filenames)\n    dataset = dataset.map(read_tfrecord, num_parallel_calls=AUTO)\n    return dataset\n\ndef gan_dataset(monet_files, photo_files, augment=None, repeat=True, shuffle=True, batch_size=1):\n    monet_ds = load_data(monet_files)\n    photo_ds = load_data(photo_files)\n    \n    if augment:\n        monet_ds = monet_ds.map(augment, num_parallel_calls=AUTO)\n        photo_ds = photo_ds.map(augment, num_parallel_calls=AUTO)\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\n# Load dataset\ndata = gan_dataset(MONET_FILES, PHOTO_FILES, augment=augment_image, repeat=True, shuffle=True, batch_size=4)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Print sample data","metadata":{}},{"cell_type":"code","source":"sample_monet , sample_photo = next(iter(data))\n\n# Display Photo images\nplt.subplot(121)\nplt.title('Photo')\nplt.imshow(sample_photo[0] * 0.5 + 0.5)\n\n# Display Monet images\nplt.subplot(122)\nplt.title('Monet')\nplt.imshow(sample_monet[0] * 0.5 + 0.5)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Main code","metadata":{}},{"cell_type":"code","source":"def down_sample(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    layer = keras.Sequential()\n    layer.add(layers.Conv2D(filters, size, strides=2, padding='same', kernel_initializer=initializer, use_bias=False))\n\n    if apply_instancenorm:\n        layer.add(tfa.layers.InstanceNormalization(gamma_initializer=gamma_init))\n\n    layer.add(layers.LeakyReLU())\n\n    return layer","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def up_sample(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    layer = keras.Sequential()\n    layer.add(layers.Conv2DTranspose(filters, size, strides=2, padding='same', kernel_initializer=initializer,use_bias=False))\n    layer.add(tfa.layers.InstanceNormalization(gamma_initializer=gamma_init))\n\n    if apply_dropout:\n        layer.add(layers.Dropout(0.5))\n\n    layer.add(layers.ReLU())\n\n    return layer","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def generator():\n    inputs = layers.Input(shape=[256,256,3])\n    down_stack = [\n        down_sample(64, 4, apply_instancenorm=False),# (size, 128, 128, 64)\n        down_sample(128, 4),                         # (size, 64, 64, 128)\n        down_sample(256, 4),                         # (size, 32, 32, 256)\n        down_sample(512, 4),                         # (size, 16, 16, 512)\n        down_sample(512, 4),                         # (size, 8, 8, 512)\n        down_sample(512, 4),                         # (size, 4, 4, 512)\n        down_sample(512, 4),                         # (size, 2, 2, 512)\n        down_sample(512, 4),                         # (size, 1, 1, 512)\n    ]\n\n    up_stack = [\n        up_sample(512, 4, apply_dropout=True),       # (size, 2, 2, 1024)\n        up_sample(512, 4, apply_dropout=True),       # (size, 4, 4, 1024)\n        up_sample(512, 4, apply_dropout=True),       # (size, 8, 8, 1024)\n        up_sample(512, 4),                           # (size, 16, 16, 1024)\n        up_sample(256, 4),                           # (size, 32, 32, 512)\n        up_sample(128, 4),                           # (size, 64, 64, 256)\n        up_sample(64, 4),                            # (size, 128, 128, 128)\n    ]\n\n    initializer = tf.random_normal_initializer(0., 0.02)\n    last = layers.Conv2DTranspose(3, 4, strides=2, padding='same', kernel_initializer=initializer, activation='tanh') \n    # (size, 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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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    x = inp\n    \n    down1 = down_sample(64, 4, False)(x)       # (size, 128, 128, 64)\n    down2 = down_sample(128, 4)(down1)         # (size, 64, 64, 128)\n    down3 = down_sample(256, 4)(down2)         # (size, 32, 32, 256)\n\n    zero_pad1 = layers.ZeroPadding2D()(down3) # (size, 34, 34, 256)\n    conv = layers.Conv2D(512, 4, strides=1, kernel_initializer=initializer, use_bias=False)(zero_pad1) # (size, 31, 31, 512)\n\n    norm1 = tfa.layers.InstanceNormalization(gamma_initializer=gamma_init)(conv)\n    leaky_relu = layers.LeakyReLU()(norm1)\n    zero_pad2 = layers.ZeroPadding2D()(leaky_relu) # (size, 33, 33, 512)\n    last = layers.Conv2D(1, 4, strides=1, kernel_initializer=initializer)(zero_pad2) # (size, 30, 30, 1)\n\n    return tf.keras.Model(inputs=inp, outputs=last)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Gan(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(Gan, 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(Gan, 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\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        }","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Generate images and send to discriminator","metadata":{}},{"cell_type":"code","source":"with strategy.scope(): # for TPU\n    monet_generator = generator() # transforms photos to Monet paintings\n    photo_generator = generator() # transforms Monet paintings to be more like photos\n\n    monet_discriminator = discriminator() # differentiates real Monet paintings and generated Monet paintings\n    photo_discriminator = discriminator() # differentiates real photos and generated photos\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Print sample generated image","metadata":{}},{"cell_type":"code","source":"to_monet = monet_generator(sample_photo) # sample run monet generator\n\nplt.subplot(1, 2, 1)\nplt.title(\"Original Photo\")\nplt.imshow(sample_photo[0] * 0.5 + 0.5) # input photo\n\nplt.subplot(1, 2, 2)\nplt.title(\"Monet Photo\")\nplt.imshow(to_monet[0] * 0.5 + 0.5) # output monet\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Generator and discriminator loss functions","metadata":{}},{"cell_type":"code","source":"with strategy.scope(): # for TPU\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        total_disc_loss = real_loss + generated_loss\n\n        return total_disc_loss * 0.5","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope(): # for TPU\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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope(): # for TPU\n    def calculate_cycle_loss(real_image, cycled_image, LAMBDA):\n        loss1 = tf.reduce_mean(tf.abs(real_image - cycled_image))\n\n        return LAMBDA * loss1","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope(): # for TPU\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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Compile GAN","metadata":{}},{"cell_type":"code","source":"with strategy.scope(): # for TPU\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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope(): # for TPU\n    gan_model = Gan(monet_generator, photo_generator, monet_discriminator, photo_discriminator)\n\n    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 = calculate_cycle_loss,\n        identity_loss_fn = identity_loss\n    )","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"gan_model.fit(data, epochs=25, steps_per_epoch=(max(n_monet, n_photo)//5))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":">### Generate and save the ouput","metadata":{}},{"cell_type":"code","source":"def 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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"os.makedirs('../images/')\npredict_and_save(load_data(PHOTO_FILES).batch(1), monet_generator, '../images/')\nshutil.make_archive('/kaggle/working/images/', 'zip', '../images')\nprint(f\"Generated samples: {len([name for name in os.listdir('../images/') if os.path.isfile(os.path.join('../images/', name))])}\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}