{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":21755,"databundleVersionId":1475600,"sourceType":"competition"}],"dockerImageVersionId":30732,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"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 20GB 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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-06-22T07:04:01.024929Z","iopub.status.idle":"2024-06-22T07:04:01.025399Z","shell.execute_reply.started":"2024-06-22T07:04:01.025195Z","shell.execute_reply":"2024-06-22T07:04:01.025212Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install tensorflow\n!pip install tensorflow-addons\n!pip install kaggle","metadata":{"execution":{"iopub.status.busy":"2024-06-22T07:04:01.031353Z","iopub.status.idle":"2024-06-22T07:04:01.031767Z","shell.execute_reply.started":"2024-06-22T07:04:01.031576Z","shell.execute_reply":"2024-06-22T07:04:01.031592Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\n\ndef load_image(image_file):\n    image = tf.io.read_file(image_file)\n    image = tf.image.decode_jpeg(image)\n    image = tf.image.resize(image, [256, 256])\n    image = (image / 127.5) - 1\n    return image\n\nmonet_dataset = tf.data.Dataset.list_files('path_to_monet_images/*.jpg')\nmonet_dataset = monet_dataset.map(load_image)\n\n# Similarly, load other datasets if needed.\n","metadata":{"execution":{"iopub.status.busy":"2024-06-22T07:04:01.033575Z","iopub.status.idle":"2024-06-22T07:04:01.034028Z","shell.execute_reply.started":"2024-06-22T07:04:01.033793Z","shell.execute_reply":"2024-06-22T07:04:01.03381Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras import layers\n\ndef build_generator():\n    model = tf.keras.Sequential()\n    model.add(layers.Input(shape=(256, 256, 3)))\n    # Add layers for the generator model\n    # For example, downsampling layers, residual blocks, and upsampling layers\n    return model\n\ndef build_discriminator():\n    model = tf.keras.Sequential()\n    model.add(layers.Input(shape=(256, 256, 3)))\n    # Add layers for the discriminator model\n    # For example, convolutional layers followed by LeakyReLU and instance normalization\n    return model\n\ngenerator_g = build_generator()\ngenerator_f = build_generator()\ndiscriminator_x = build_discriminator()\ndiscriminator_y = build_discriminator()\n","metadata":{"execution":{"iopub.status.busy":"2024-06-22T07:04:01.035637Z","iopub.status.idle":"2024-06-22T07:04:01.036099Z","shell.execute_reply.started":"2024-06-22T07:04:01.035859Z","shell.execute_reply":"2024-06-22T07:04:01.035875Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"loss_obj = tf.keras.losses.BinaryCrossentropy(from_logits=True)\n\ndef discriminator_loss(real, generated):\n    real_loss = loss_obj(tf.ones_like(real), real)\n    generated_loss = loss_obj(tf.zeros_like(generated), generated)\n    total_disc_loss = real_loss + generated_loss\n    return total_disc_loss * 0.5\n\ndef generator_loss(generated):\n    return loss_obj(tf.ones_like(generated), generated)\n\ncycle_loss = tf.keras.losses.MeanAbsoluteError()\nLAMBDA = 10\n\ndef calc_cycle_loss(real_image, cycled_image):\n    return LAMBDA * cycle_loss(real_image, cycled_image)\n\ndef identity_loss(real_image, same_image):\n    return LAMBDA * 0.5 * cycle_loss(real_image, same_image)\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)\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","metadata":{"execution":{"iopub.status.busy":"2024-06-22T07:04:04.387027Z","iopub.execute_input":"2024-06-22T07:04:04.387462Z","iopub.status.idle":"2024-06-22T07:04:04.463975Z","shell.execute_reply.started":"2024-06-22T07:04:04.387426Z","shell.execute_reply":"2024-06-22T07:04:04.462593Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import datetime\n\n@tf.function\ndef train_step(real_x, real_y):\n    with tf.GradientTape(persistent=True) as tape:\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, generator_g.trainable_variables)\n    generator_f_gradients = tape.gradient(total_gen_f_loss, generator_f.trainable_variables)\n    discriminator_x_gradients = tape.gradient(disc_x_loss, discriminator_x.trainable_variables)\n    discriminator_y_gradients = tape.gradient(disc_y_loss, discriminator_y.trainable_variables)\n\n    generator_g_optimizer.apply_gradients(zip(generator_g_gradients, generator_g.trainable_variables))\n    generator_f_optimizer.apply_gradients(zip(generator_f_gradients, generator_f.trainable_variables))\n    discriminator_x_optimizer.apply_gradients(zip(discriminator_x_gradients, discriminator_x.trainable_variables))\n    discriminator_y_optimizer.apply_gradients(zip(discriminator_y_gradients, discriminator_y.trainable_variables))\n\ndef fit(dataset, epochs):\n    for epoch in range(epochs):\n        start = datetime.datetime.now()\n        for image_x, image_y in dataset:\n            train_step(image_x, image_y)\n        print(f'Time taken for epoch {epoch + 1} is {datetime.datetime.now() - start}')\n\n# Assuming combined_dataset is a combination of Monet and other images\nfit(combined_dataset, epochs=100)\n","metadata":{"execution":{"iopub.status.busy":"2024-06-22T07:06:10.753703Z","iopub.execute_input":"2024-06-22T07:06:10.754169Z","iopub.status.idle":"2024-06-22T07:06:10.82707Z","shell.execute_reply.started":"2024-06-22T07:06:10.754131Z","shell.execute_reply":"2024-06-22T07:06:10.825412Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nfrom PIL import Image\nimport numpy as np\n\ndef generate_images(model, test_input, output_dir, num_images=7000):\n    if not os.path.exists(output_dir):\n        os.makedirs(output_dir)\n    for i in range(num_images):\n        prediction = model(test_input, training=False)\n        img = ((prediction[0].numpy() + 1) * 127.5).astype(np.uint8)\n        img = Image.fromarray(img)\n        img.save(f'{output_dir}/image_{i}.jpg')\n\ngenerate_images(generator_g, monet_dataset.take(1), 'output_images', num_images=7000)\n","metadata":{"execution":{"iopub.status.busy":"2024-06-22T07:04:36.305156Z","iopub.execute_input":"2024-06-22T07:04:36.305545Z","iopub.status.idle":"2024-06-22T07:04:36.35883Z","shell.execute_reply.started":"2024-06-22T07:04:36.305517Z","shell.execute_reply":"2024-06-22T07:04:36.35694Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import zipfile\n\ndef zip_dir(folder_path, zip_path):\n    with zipfile.ZipFile(zip_path, 'w') as zipf:\n        for root, _, files in os.walk(folder_path):\n            for file in files:\n                zipf.write(os.path.join(root, file), arcname=file)\n\nzip_dir('output_images', 'images.zip')\n","metadata":{"execution":{"iopub.status.busy":"2024-06-22T07:04:45.044813Z","iopub.execute_input":"2024-06-22T07:04:45.045235Z","iopub.status.idle":"2024-06-22T07:04:45.052989Z","shell.execute_reply.started":"2024-06-22T07:04:45.045202Z","shell.execute_reply":"2024-06-22T07:04:45.051465Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}