{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","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":30804,"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\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T12:52:55.644532Z","iopub.execute_input":"2024-12-21T12:52:55.644862Z","iopub.status.idle":"2024-12-21T12:53:04.207346Z","shell.execute_reply.started":"2024-12-21T12:52:55.644818Z","shell.execute_reply":"2024-12-21T12:53:04.206124Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras import layers\nimport numpy as np\nimport os\nfrom zipfile import ZipFile\n\n\ndef spectral_norm(layer):\n    return layers.LayerNormalization()(layer)\n \ndef build_generator():\n    model = tf.keras.Sequential([\n        layers.Dense(8*8*512, use_bias=False, input_shape=(100,)),\n        layers.Reshape((8, 8, 512)),\n        layers.Conv2DTranspose(256, (5, 5), strides=(2, 2), padding='same', use_bias=False),\n        layers.BatchNormalization(), layers.LeakyReLU(),\n        layers.Conv2DTranspose(128, (5, 5), strides=(2, 2), padding='same', use_bias=False),\n        layers.BatchNormalization(), layers.LeakyReLU(),\n        layers.Conv2DTranspose(64, (5, 5), strides=(2, 2), padding='same', use_bias=False),\n        layers.BatchNormalization(), layers.LeakyReLU(),\n        layers.Conv2DTranspose(32, (5, 5), strides=(2, 2), padding='same', use_bias=False),\n        layers.BatchNormalization(), layers.LeakyReLU(),\n        layers.Conv2DTranspose(3, (5, 5), strides=(2, 2), padding='same', use_bias=False, activation='tanh')\n    ])\n    return model\n\ndef build_discriminator():\n    model = tf.keras.Sequential([\n        layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same', input_shape=[256, 256, 3]),\n        layers.LeakyReLU(),\n        layers.Dropout(0.3),\n        layers.Conv2D(128, (5, 5), strides=(2, 2), padding='same'),\n        layers.LeakyReLU(),\n        layers.Dropout(0.3),\n        layers.Conv2D(256, (5, 5), strides=(2, 2), padding='same'),\n        layers.LeakyReLU(),\n        layers.Dropout(0.3),\n        layers.Flatten(),\n        layers.Dense(1)\n    ])\n    return model\n\ngenerator = build_generator()\ndiscriminator = build_discriminator()\n\ndef preprocess_image(image):\n    image = tf.image.resize(image, (256, 256))\n    image = (image - 127.5) / 127.5\n    return image\n\ndef load_dataset():\n    dataset = tf.data.Dataset.from_tensor_slices(np.random.random((1000, 256, 256, 3))).batch(32)\n    dataset = dataset.map(preprocess_image)\n    return dataset\n\n@tf.function\ndef wasserstein_loss(real_output, fake_output):\n    return tf.reduce_mean(fake_output) - tf.reduce_mean(real_output)\n\n@tf.function\ndef train_step(generator, discriminator, generator_optimizer, discriminator_optimizer, images):\n    batch_size = tf.shape(images)[0]\n    noise = tf.random.normal([batch_size, 100])\n    \n    with tf.GradientTape(persistent=True) as tape:\n        fake_images = generator(noise, training=True)\n        real_output = discriminator(images, training=True)\n        fake_output = discriminator(fake_images, training=True)\n        \n        d_loss = wasserstein_loss(real_output, fake_output)\n        g_loss = -tf.reduce_mean(fake_output)\n\n    grads_gen = tape.gradient(g_loss, generator.trainable_variables)\n    grads_disc = tape.gradient(d_loss, discriminator.trainable_variables)\n    generator_optimizer.apply_gradients(zip(grads_gen, generator.trainable_variables))\n    discriminator_optimizer.apply_gradients(zip(grads_disc, discriminator.trainable_variables))\n    \n    return d_loss, g_loss\n\n\ndef train_gan(generator, discriminator, dataset, epochs, output_dir):\n    generator_optimizer = tf.keras.optimizers.Adam(1e-4)\n    discriminator_optimizer = tf.keras.optimizers.Adam(1e-4)\n\n    zip_file = ZipFile('images.zip', 'w')\n    image_counter = 0\n\n    for epoch in range(epochs):\n        for images in dataset:\n            d_loss, g_loss = train_step(generator, discriminator, generator_optimizer, discriminator_optimizer, images)\n\n        print(f\"Epoch {epoch + 1}/{epochs}: D_loss={d_loss:.4f}, G_loss={g_loss:.4f}\")\n\n        for _ in range(700):\n            noise = tf.random.normal([1, 100])\n            generated_image = generator(noise, training=False)\n            image = (generated_image[0] * 127.5 + 127.5).numpy().astype(np.uint8)\n            image_path = f'{output_dir}/image_{image_counter}.jpg'\n            tf.keras.utils.save_img(image_path, image)\n            zip_file.write(image_path, arcname=f'image_{image_counter}.jpg')\n            image_counter += 1\n \n    zip_file.close() \n\noutput_dir = '/kaggle/working/tmp'\nos.makedirs(output_dir, exist_ok=True)\ndataset = load_dataset()  \ntrain_gan(generator, discriminator, dataset, epochs=10, output_dir=output_dir) ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-21T12:53:04.209432Z","iopub.execute_input":"2024-12-21T12:53:04.210037Z"}},"outputs":[],"execution_count":null}]}