{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"!pip install -q git+https://github.com/tensorflow/examples.git","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow_examples.models.pix2pix import pix2pix\nimport matplotlib.pyplot as plt\nfrom kaggle_datasets import KaggleDatasets\nfrom IPython.display import clear_output\nimport numpy as np\n\nAUTOTUNE = tf.data.experimental.AUTOTUNE","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_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))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_SIZE = [256,256]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def decode_image(image):\n    image = tf.image.decode_jpeg(image, channels=3)\n    image = tf.cast(image, tf.float32) / 127.5 - 1.0\n    image = tf.reshape(image, [*IMAGE_SIZE,3])\n    return image\n\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\n\ndef 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"monet_ds = load_dataset(MONET_FILENAMES, labeled=True).batch(1)\nphoto_ds = load_dataset(PHOTO_FILENAMES, labeled=True).batch(1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"monet = next(iter(monet_ds))\nphoto = next(iter(photo_ds))\n\nplt.figure(figsize=(10,20))\nfor i,image in enumerate([photo, monet]):\n    plt.subplot(1,2,i+1)\n    plt.imshow(image[0] * 0.5 + 0.5)\n    plt.axis('off')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"OUTPUT_CHANNELS = 3\n\ngenerator_g = pix2pix.unet_generator(OUTPUT_CHANNELS, norm_type='instancenorm')\ngenerator_f = pix2pix.unet_generator(OUTPUT_CHANNELS, norm_type='instancenorm')\n\ndiscriminator_x = pix2pix.discriminator(norm_type='instancenorm', target=False)\ndiscriminator_y = pix2pix.discriminator(norm_type='instancenorm', target=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"LAMBDA = 10\nloss_obj = tf.keras.losses.BinaryCrossentropy(from_logits=True)\ndef discriminator_loss(real, generated):\n    real_loss = loss_obj(tf.ones_like(real), real)\n\n    generated_loss = loss_obj(tf.zeros_like(generated), generated)\n\n    total_disc_loss = real_loss + generated_loss\n\n    return total_disc_loss * 0.5\n\n\ndef generator_loss(generated):\n    return loss_obj(tf.ones_like(generated), generated)\n\n\ndef calc_cycle_loss(real_image, cycled_image):\n  loss1 = tf.reduce_mean(tf.abs(real_image - cycled_image))\n  return LAMBDA * loss1\n\n\ndef identity_loss(real_image, same_image):\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":"generator_g_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\ngenerator_f_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n\ndiscriminator_x_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\ndiscriminator_y_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def generate_images(model, test_input):\n    prediction = model(test_input)\n\n    plt.figure(figsize=(12, 12))\n\n    display_list = [test_input[0], prediction[0]]\n    title = ['Input Image', 'Predicted Image']\n\n    for i in range(2):\n        plt.subplot(1, 2, i+1)\n        plt.title(title[i])\n        plt.imshow(display_list[i] * 0.5 + 0.5)\n        plt.axis('off')\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"@tf.function\ndef train_step(real_x, real_y):\n    with tf.GradientTape(persistent=True) as tape:\n\n        fake_y = generator_g(real_x, training=True)\n        cycled_x = generator_f(fake_y, training=True)\n\n        fake_x = generator_f(real_y, training=True)\n        cycled_y = generator_g(fake_x, training=True)\n\n        same_x = generator_f(real_x, training=True)\n        same_y = generator_g(real_y, training=True)\n\n        disc_real_x = discriminator_x(real_x, training=True)\n        disc_real_y = discriminator_y(real_y, training=True)\n\n        disc_fake_x = discriminator_x(fake_x, training=True)\n        disc_fake_y = discriminator_y(fake_y, training=True)\n\n        gen_g_loss = generator_loss(disc_fake_y)\n        gen_f_loss = generator_loss(disc_fake_x)\n\n        total_cycle_loss = calc_cycle_loss(real_x, cycled_x) + calc_cycle_loss(real_y, cycled_y)\n\n        total_gen_g_loss = gen_g_loss + total_cycle_loss + identity_loss(real_y, same_y)\n        total_gen_f_loss = gen_f_loss + total_cycle_loss + identity_loss(real_x, same_x)\n\n        disc_x_loss = discriminator_loss(disc_real_x, disc_fake_x)\n        disc_y_loss = discriminator_loss(disc_real_y, disc_fake_y)\n  \n    generator_g_gradients = tape.gradient(total_gen_g_loss, \n                                        generator_g.trainable_variables)\n    generator_f_gradients = tape.gradient(total_gen_f_loss, \n                                        generator_f.trainable_variables)\n\n    discriminator_x_gradients = tape.gradient(disc_x_loss, \n                                            discriminator_x.trainable_variables)\n    discriminator_y_gradients = tape.gradient(disc_y_loss, \n                                            discriminator_y.trainable_variables)\n\n    generator_g_optimizer.apply_gradients(zip(generator_g_gradients, \n                                            generator_g.trainable_variables))\n\n    generator_f_optimizer.apply_gradients(zip(generator_f_gradients, \n                                            generator_f.trainable_variables))\n\n    discriminator_x_optimizer.apply_gradients(zip(discriminator_x_gradients,\n                                                discriminator_x.trainable_variables))\n\n    discriminator_y_optimizer.apply_gradients(zip(discriminator_y_gradients,\n                                                discriminator_y.trainable_variables))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_monet = next(iter(monet_ds))\nsample_photo = next(iter(photo_ds))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"EPOCHS = 200\nfor epoch in range(EPOCHS):\n    n = 0\n    for image_x, image_y in tf.data.Dataset.zip((photo_ds, monet_ds)):\n        train_step(image_x, image_y)\n        if n % 10 == 0:\n            print ('.', end='')\n        n+=1\n\n    clear_output(wait=True)\n    generate_images(generator_g, sample_photo)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for inp in photo_ds.take(10):\n  generate_images(generator_g, inp)","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 photo_ds:\n    prediction = generator_g(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","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":{"trusted":true},"cell_type":"code","source":"","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}