{"cells":[{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nimport tensorflow_addons as tfa\n! pip install -q git+https://github.com/tensorflow/examples.git\nfrom tensorflow_examples.models.pix2pix import pix2pix\nimport time\nimport matplotlib.pyplot as plt\nfrom IPython.display import clear_output\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__)\n\nGCS_PATH = KaggleDatasets().get_gcs_path()\n\n# https://www.tensorflow.org/hub/tutorials/tf2_arbitrary_image_stylization \n#import tensorflow_hub as hub\n#hub_handle = 'https://tfhub.dev/google/magenta/arbitrary-image-stylization-v1-256/2'\n#hub_module = hub.load(hub_handle)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"IMAGE_SIZE = [256, 256]\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))\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\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\n\nmonet_ds = load_dataset(MONET_FILENAMES, labeled=True).batch(1)\nphoto_ds = load_dataset(PHOTO_FILENAMES, labeled=True).batch(1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":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,"scrolled":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\ndef generator_loss(generated):\n  return loss_obj(tf.ones_like(generated), generated)\ndef calc_cycle_loss(real_image, cycled_image):\n  loss1 = tf.reduce_mean(tf.abs(real_image - cycled_image))\n\n  return LAMBDA * loss1\ndef identity_loss(real_image, same_image):\n  loss = tf.reduce_mean(tf.abs(real_image - same_image))\n  return LAMBDA * 0.5 * loss\n\ngenerator_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)\n\ncheckpoint_path = \"./checkpoints/train\"\n\nckpt = tf.train.Checkpoint(generator_g=generator_g,\n                           generator_f=generator_f,\n                           discriminator_x=discriminator_x,\n                           discriminator_y=discriminator_y,\n                           generator_g_optimizer=generator_g_optimizer,\n                           generator_f_optimizer=generator_f_optimizer,\n                           discriminator_x_optimizer=discriminator_x_optimizer,\n                           discriminator_y_optimizer=discriminator_y_optimizer)\n\nckpt_manager = tf.train.CheckpointManager(ckpt, checkpoint_path, max_to_keep=5)\n\n# if a checkpoint exists, restore the latest checkpoint.\nif ckpt_manager.latest_checkpoint:\n  ckpt.restore(ckpt_manager.latest_checkpoint)\n  print ('Latest checkpoint restored!!')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"EPOCHS = 35\n\ndef 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    # getting the pixel values between [0, 1] to plot it.\n    plt.imshow(display_list[i] * 0.5 + 0.5)\n    plt.axis('off')\n  plt.show()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"@tf.function\ndef train_step(real_x, real_y):\n  # persistent is set to True because the tape is used more than\n  # once to calculate the gradients.\n  with tf.GradientTape(persistent=True) as tape:\n    # Generator G translates X -> Y\n    # Generator F translates Y -> X.\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 and same_y are used for identity loss.\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    # calculate the loss\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 generator loss = adversarial loss + cycle loss\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  # Calculate the gradients for generator and discriminator\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  # Apply the gradients to the optimizer\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,"scrolled":true},"cell_type":"code","source":"sample_horse = next(iter(photo_ds)) # photo images we want to be the input\nplt.subplot(121)\nplt.title('Horse')\nplt.imshow(sample_horse[0] * 0.5 + 0.5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"for epoch in range(EPOCHS):\n  start = time.time()\n\n  n = 0\n  for image_x, image_y in tf.data.Dataset.zip((monet_ds, photo_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  # Using a consistent image (sample_horse) so that the progress of the model\n  # is clearly visible.\n  generate_images(generator_g, sample_horse)\n\n  if (epoch + 1) % 5 == 0:\n    ckpt_save_path = ckpt_manager.save()\n    print ('Saving checkpoint for epoch {} at {}'.format(epoch+1,\n                                                         ckpt_save_path))\n\n  print ('Time taken for epoch {} is {} sec\\n'.format(epoch + 1,\n                                                      time.time()-start))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"import PIL\n! mkdir ../images","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"i = 1\nstart = time.time()\nfor img in photo_ds:\n    prediction = generator_g(img)[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\n    if i % 1000 == 0:\n        print(\"all ok till , \", i)\n\nprint(time.time()-start)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"import shutil\nshutil.make_archive(\"/kaggle/working/images\", 'zip', \"/kaggle/images\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"plt.imshow(generator_g(img)[0] * 0.5 + 0.5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":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}