{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%cd ../\n!mkdir temp\n%cd temp/\n!ls","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n!ls","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dir","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pwd","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":""},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","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\nimport tensorflow_datasets as tfds\nfrom tensorflow_examples.models.pix2pix import pix2pix\nimport tensorflow_addons as tfa\nimport os\nimport time\nimport matplotlib.pyplot as plt\nfrom IPython.display import clear_output\nimport numpy as np\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nimport tensorflow_addons as tfa\nfrom kaggle_datasets import KaggleDatasets\n\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__)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"GCS_PATH = KaggleDatasets().get_gcs_path()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"MONET_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]\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"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=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":"sample_monet = next(iter(monet_ds))\nsample_photo = next(iter(photo_ds))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.subplot(121)\nplt.title('Photo')\nplt.imshow(sample_photo[0] * 0.5 + 0.5)\n\nplt.subplot(122)\nplt.title('Monet')\nplt.imshow(sample_monet[0] * 0.5 + 0.5)","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":"to_monet = generator_g(sample_photo)\nto_photo = generator_f(sample_monet)\nplt.figure(figsize=(8, 8))\ncontrast = 8\n\nimgs = [sample_photo, to_monet, sample_monet, to_photo]\ntitle = ['Photo', 'To Monet', 'Monet', 'To Photo']\n\nfor i in range(len(imgs)):\n  plt.subplot(2, 2, i+1)\n  plt.title(title[i])\n  if i % 2 == 0:\n    plt.imshow(imgs[i][0] * 0.5 + 0.5)\n  else:\n    plt.imshow(imgs[i][0] * 0.5 * contrast + 0.5)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(8, 8))\n\nplt.subplot(121)\nplt.title('real monet?')\nplt.imshow(discriminator_y(sample_monet)[0, ..., -1], cmap='RdBu_r')\n\nplt.subplot(122)\nplt.title('real photo?')\nplt.imshow(discriminator_x(sample_photo)[0, ..., -1], cmap='RdBu_r')\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"LAMBDA = 10\n\nloss_obj = tf.keras.losses.BinaryCrossentropy(from_logits=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def generator_loss(generated):\n  return loss_obj(tf.ones_like(generated), generated)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def calc_cycle_loss(real_image, cycled_image):\n  loss1 = tf.reduce_mean(tf.abs(real_image - cycled_image))\n  \n  return LAMBDA * loss1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def 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":"checkpoint_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},"cell_type":"code","source":"EPOCHS = 50","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    # 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()","execution_count":null,"outputs":[]},{"metadata":{"trusted":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},"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((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  # Using a consistent image (sample_horse) so that the progress of the model\n  # is clearly visible.\n  generate_images(generator_g, sample_photo)\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},"cell_type":"code","source":"%cd ../\n!ls","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import urllib.request\n\nprint('Beginning file download with urllib2...')\n\nurl = 'https://www.kaggle.com/next/kernels/notebook-e28cd55b881df1e72aef.js?62303ea8088ef288315f/kaggle/temp/checkpoints/train/ckpt-10'\nurllib.request.urlretrieve(url, '/Users/Chel/Downloads')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%cd train\n!ls","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}