{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# **Using GANs to Create Monet Style Art (CycleGAN)**\n\nTable of Contents:\n* [About the Data / Project](#about)\n* [Set Up](#set)\n* [Exploratory Data Analysis](#eda)\n* [Building the Generator](#gen)\n* [Building the Discriminator](#disc)\n* [Building CycleGAN](#gan)\n* [Defining Loss Functions](#loss)\n* [Training the Model](#model)\n* [Results](#results)\n* [Submission](#sub)\n* [Conclusion](#conclusion)\n* [References](#ref)","metadata":{}},{"cell_type":"markdown","source":"<a id=\"about\"></a>\n# **About the Data / Project**","metadata":{}},{"cell_type":"markdown","source":"This dataset can be found in the [Kaggle](https://www.kaggle.com/competitions/gan-getting-started) \"I'm Something of a Painter Myself\" competition. The dataset contains four directories: monet_tfrec, photo_tfrec, monet_jpg, and photo_jpg. The monet directories contain 300 Monet paintings with a size of 256x256 pixels. The monet_jpg directory contains these 300 paintings in JPEG format, while the monet_tfrec directory contains them in TFRecord format. The photo directories contain 7028 photos sized 256x256 pixels. Again, photo_jpg and photo_tfrec have the photos in JPEG and TFRecord format, respectively. \n\nThe task of this competition and therefore this project is to develop a generative adversarial network (GAN) which will work to convert regular photos into Monet style paintings. According to Kaggle, a GAN is made up of at least two neural networks, i.e. a generator model and a discriminator model. As this is an adversarial model, the generator and the discriminator will work in opposition to eventually create more and more realistic Monet style images. In this project, I will employ the use of [CycleGAN](https://www.tensorflow.org/tutorials/generative/cyclegan). According to the tensorflow website, CycleGAN is able to train without the use of paired data, as the GAN employs an additional cycle consistency loss function. This proves to be beneficial, as CycleGAN can translate between two domains without having a one-to-one mapping between them. Because of this, CycleGAN is able to do tasks such as style transfer, which is the main objective of this project.  ","metadata":{}},{"cell_type":"markdown","source":"<a id=\"set\"></a>\n# **Set Up**","metadata":{}},{"cell_type":"code","source":"# Loading necessary packages\nimport os\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport seaborn as sns\nimport tensorflow as tf\nimport tensorflow_addons as tfa\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nimport cv2\nfrom kaggle_datasets import KaggleDatasets\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__)","metadata":{"_kg_hide-input":false,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-07-21T15:58:49.753978Z","iopub.execute_input":"2023-07-21T15:58:49.754373Z","iopub.status.idle":"2023-07-21T15:58:59.492092Z","shell.execute_reply.started":"2023-07-21T15:58:49.754340Z","shell.execute_reply":"2023-07-21T15:58:59.490354Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Loading monet and photo directories for EDA\nmonet_eda = \"../input/gan-getting-started/monet_jpg\"\nphoto_eda = \"../input/gan-getting-started/photo_jpg\"","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:58:59.494058Z","iopub.execute_input":"2023-07-21T15:58:59.495059Z","iopub.status.idle":"2023-07-21T15:58:59.500299Z","shell.execute_reply.started":"2023-07-21T15:58:59.495023Z","shell.execute_reply":"2023-07-21T15:58:59.499378Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Creating image_path function to retrieve image paths from directory\ndef image_path(path):\n    image_names = []\n    for dirname, _, filenames in os.walk(path):\n        for filename in filenames:\n            fullpath = os.path.join(dirname, filename)\n            image_names.append(fullpath)\n    return image_names","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:58:59.503544Z","iopub.execute_input":"2023-07-21T15:58:59.503852Z","iopub.status.idle":"2023-07-21T15:58:59.513713Z","shell.execute_reply.started":"2023-07-21T15:58:59.503827Z","shell.execute_reply":"2023-07-21T15:58:59.512783Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Applying image_path function to monet_eda and photo_eda datasets\nmonet_eda1 = image_path(monet_eda)\nphoto_eda1 = image_path(photo_eda)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:58:59.517761Z","iopub.execute_input":"2023-07-21T15:58:59.518696Z","iopub.status.idle":"2023-07-21T15:59:06.086848Z","shell.execute_reply.started":"2023-07-21T15:58:59.518514Z","shell.execute_reply":"2023-07-21T15:59:06.084973Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"In the code chunks above, the monet_jpg and photo_jpg directories have been imported and loaded for the sole use of a brief exploratory data analysis. Below,the .tfrec directories will be loaded and used for the CycleGAN model. ","metadata":{}},{"cell_type":"code","source":"# Creating path for .tfrec directories\npath = KaggleDatasets().get_gcs_path()","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:06.091851Z","iopub.execute_input":"2023-07-21T15:59:06.093439Z","iopub.status.idle":"2023-07-21T15:59:06.593803Z","shell.execute_reply.started":"2023-07-21T15:59:06.093402Z","shell.execute_reply":"2023-07-21T15:59:06.592828Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Pulling in filenames of monet_tfrec and photo_tfrec\nmonet_filenames = tf.io.gfile.glob(str(path + '/monet_tfrec/*.tfrec'))\nphoto_filenames = tf.io.gfile.glob(str(path + '/photo_tfrec/*.tfrec'))","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:06.595196Z","iopub.execute_input":"2023-07-21T15:59:06.595580Z","iopub.status.idle":"2023-07-21T15:59:06.770640Z","shell.execute_reply.started":"2023-07-21T15:59:06.595545Z","shell.execute_reply":"2023-07-21T15:59:06.769828Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Checking number of monet and photo TFRecord files\nprint('Monet TFRecord Files: ', len(monet_filenames))\nprint('Photo TFRecord Files: ', len(photo_filenames))","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:06.772306Z","iopub.execute_input":"2023-07-21T15:59:06.772622Z","iopub.status.idle":"2023-07-21T15:59:06.778332Z","shell.execute_reply.started":"2023-07-21T15:59:06.772591Z","shell.execute_reply":"2023-07-21T15:59:06.777425Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Above, we can see the number of TFRecord filenames in the monet and photo datasets. This files include the 300 Monet images and 7038 photos which we will load in soon.","metadata":{}},{"cell_type":"code","source":"# Creating decode_image function\nIMAGE_SIZE = [256, 256]\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","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:06.779537Z","iopub.execute_input":"2023-07-21T15:59:06.780034Z","iopub.status.idle":"2023-07-21T15:59:06.789285Z","shell.execute_reply.started":"2023-07-21T15:59:06.780003Z","shell.execute_reply":"2023-07-21T15:59:06.788411Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Creating read_tfrecord function\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","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:06.790406Z","iopub.execute_input":"2023-07-21T15:59:06.791394Z","iopub.status.idle":"2023-07-21T15:59:06.802486Z","shell.execute_reply.started":"2023-07-21T15:59:06.791344Z","shell.execute_reply":"2023-07-21T15:59:06.801423Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The functions decode_image and read_tfrecord above will work to help extract images from the monet_filenames and photo_filenames datasets. All images in the datasets are already set to 256x256 pixels and the channel has been set to 3, as all images are RGB images. The functions above will scale these images to a [-1,1] scale and will remove labels and image ids. ","metadata":{}},{"cell_type":"code","source":"# Creating load_dataset function\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","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:06.807660Z","iopub.execute_input":"2023-07-21T15:59:06.807952Z","iopub.status.idle":"2023-07-21T15:59:06.814750Z","shell.execute_reply.started":"2023-07-21T15:59:06.807928Z","shell.execute_reply":"2023-07-21T15:59:06.813871Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Loading in datasets with images\nmonet_ds = load_dataset(monet_filenames, labeled=True).batch(1)\nphoto_ds = load_dataset(photo_filenames, labeled=True).batch(1)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:06.816341Z","iopub.execute_input":"2023-07-21T15:59:06.816736Z","iopub.status.idle":"2023-07-21T15:59:09.981314Z","shell.execute_reply.started":"2023-07-21T15:59:06.816702Z","shell.execute_reply":"2023-07-21T15:59:09.980313Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"example_monet = next(iter(monet_ds))\nexample_photo = next(iter(photo_ds))","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:09.982651Z","iopub.execute_input":"2023-07-21T15:59:09.982989Z","iopub.status.idle":"2023-07-21T15:59:11.141736Z","shell.execute_reply.started":"2023-07-21T15:59:09.982958Z","shell.execute_reply":"2023-07-21T15:59:11.140712Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"eda\"></a>\n# **Exploratory Data Analysis**","metadata":{}},{"cell_type":"code","source":"# Viewing number of images in monet and photo datasets\nprint(\"Monet Images: \", len(monet_eda1))\nprint(\"Photo Images: \", len(photo_eda1))","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:11.143169Z","iopub.execute_input":"2023-07-21T15:59:11.143530Z","iopub.status.idle":"2023-07-21T15:59:11.149982Z","shell.execute_reply.started":"2023-07-21T15:59:11.143498Z","shell.execute_reply":"2023-07-21T15:59:11.148971Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Above, we can confirm the amount of images in each dataset. There are 300 images in the monet dataset and 7038 images in the photo dataset. It should be noted that while Kaggle states that there are 7028 photos in the photo directories, the code chunk above has yielded a number of 7038. Fortunately, this is a relatively small difference, and thus will not likely affect the training. ","metadata":{}},{"cell_type":"code","source":"# Creating display function to show image examples\ndef display(images_paths, rows, cols):\n    figure, ax = plt.subplots(nrows=rows,ncols=cols,figsize=(16,8) )\n    for ind,image_path in enumerate(images_paths):\n        image=cv2.imread(image_path)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) \n        try:\n            ax.ravel()[ind].imshow(image)\n            ax.ravel()[ind].set_axis_off()\n        except:\n            continue;\n    plt.tight_layout()\n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:11.151255Z","iopub.execute_input":"2023-07-21T15:59:11.152142Z","iopub.status.idle":"2023-07-21T15:59:11.161406Z","shell.execute_reply.started":"2023-07-21T15:59:11.152110Z","shell.execute_reply":"2023-07-21T15:59:11.160443Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Viewing examples of images in monet_eda dataset\ndisplay(monet_eda1,3,3)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:11.162530Z","iopub.execute_input":"2023-07-21T15:59:11.163504Z","iopub.status.idle":"2023-07-21T15:59:13.883725Z","shell.execute_reply.started":"2023-07-21T15:59:11.163472Z","shell.execute_reply":"2023-07-21T15:59:13.881825Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Viewing examples of images in photo_eda dataset\ndisplay(photo_eda1,3,3)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:13.884757Z","iopub.execute_input":"2023-07-21T15:59:13.885086Z","iopub.status.idle":"2023-07-21T15:59:58.939360Z","shell.execute_reply.started":"2023-07-21T15:59:13.885056Z","shell.execute_reply":"2023-07-21T15:59:58.938520Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Above, we can see several examples of the Monet paintings and the photos that are available in the datasets. At a glance, there is an obvious difference between the example sets. The photos are clear images while the Monet paintings have somewhat of a softer resolution. It will definitely be interesting to see how the GAN converts the photos into a Monet style work. ","metadata":{}},{"cell_type":"markdown","source":"<a id=\"gen\"></a>\n# **Building the Generator**","metadata":{}},{"cell_type":"markdown","source":"As this is my first attempt at using CycleGAN, the following sections has been heavily influenced by a model tutorial created by [Amy Jang](https://www.kaggle.com/code/amyjang/monet-cyclegan-tutorial). ","metadata":{}},{"cell_type":"code","source":"# Creating downsample function\nOUTPUT_CHANNELS = 3\n\ndef downsample(filters, size, apply_instancenorm=True):\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gamma_init = keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n    result = keras.Sequential()\n    result.add(layers.Conv2D(filters, size, strides=2, padding='same',\n                             kernel_initializer=initializer, use_bias=False))\n    if apply_instancenorm:\n        result.add(tfa.layers.InstanceNormalization(gamma_initializer=gamma_init))\n    result.add(layers.LeakyReLU())\n    return result","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:58.940699Z","iopub.execute_input":"2023-07-21T15:59:58.941534Z","iopub.status.idle":"2023-07-21T15:59:58.949731Z","shell.execute_reply.started":"2023-07-21T15:59:58.941498Z","shell.execute_reply":"2023-07-21T15:59:58.948676Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The downsample function above works to reduce the dimensions (height and width) of images by a stride of 2. ","metadata":{}},{"cell_type":"code","source":"# Creating upsample function\ndef upsample(filters, size, apply_dropout=False):\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gamma_init = keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n    result = keras.Sequential()\n    result.add(layers.Conv2DTranspose(filters, size, strides=2,\n                                      padding='same',\n                                      kernel_initializer=initializer,\n                                      use_bias=False))\n    result.add(tfa.layers.InstanceNormalization(gamma_initializer=gamma_init))\n    if apply_dropout:\n        result.add(layers.Dropout(0.5))\n    result.add(layers.ReLU())\n    return result","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:58.951563Z","iopub.execute_input":"2023-07-21T15:59:58.951985Z","iopub.status.idle":"2023-07-21T15:59:58.971145Z","shell.execute_reply.started":"2023-07-21T15:59:58.951955Z","shell.execute_reply":"2023-07-21T15:59:58.969994Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The upsample function above works in an opposite manner when compared to the downsample function. Instead, the upsample function works to increase the dimensions of images by a stride of 2. ","metadata":{}},{"cell_type":"code","source":"# Creating the Generator! \ndef Generator():\n    inputs = layers.Input(shape=[256,256,3])\n\n    # bs = batch size\n    down_stack = [\n        downsample(64, 4, apply_instancenorm=False), # (bs, 128, 128, 64)\n        downsample(128, 4), # (bs, 64, 64, 128)\n        downsample(256, 4), # (bs, 32, 32, 256)\n        downsample(512, 4), # (bs, 16, 16, 512)\n        downsample(512, 4), # (bs, 8, 8, 512)\n        downsample(512, 4), # (bs, 4, 4, 512)\n        downsample(512, 4), # (bs, 2, 2, 512)\n        downsample(512, 4), # (bs, 1, 1, 512)\n    ]\n\n    up_stack = [\n        upsample(512, 4, apply_dropout=True), # (bs, 2, 2, 1024)\n        upsample(512, 4, apply_dropout=True), # (bs, 4, 4, 1024)\n        upsample(512, 4, apply_dropout=True), # (bs, 8, 8, 1024)\n        upsample(512, 4), # (bs, 16, 16, 1024)\n        upsample(256, 4), # (bs, 32, 32, 512)\n        upsample(128, 4), # (bs, 64, 64, 256)\n        upsample(64, 4), # (bs, 128, 128, 128)\n    ]\n\n    initializer = tf.random_normal_initializer(0., 0.02)\n    last = layers.Conv2DTranspose(OUTPUT_CHANNELS, 4,\n                                  strides=2,\n                                  padding='same',\n                                  kernel_initializer=initializer,\n                                  activation='tanh') # (bs, 256, 256, 3)\n\n    x = inputs\n\n    # Downsampling through the model\n    skips = []\n    for down in down_stack:\n        x = down(x)\n        skips.append(x)\n\n    skips = reversed(skips[:-1])\n\n    # Upsampling and establishing the skip connections\n    for up, skip in zip(up_stack, skips):\n        x = up(x)\n        x = layers.Concatenate()([x, skip])\n\n    x = last(x)\n\n    return keras.Model(inputs=inputs, outputs=x)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:58.973059Z","iopub.execute_input":"2023-07-21T15:59:58.973455Z","iopub.status.idle":"2023-07-21T15:59:58.987562Z","shell.execute_reply.started":"2023-07-21T15:59:58.973426Z","shell.execute_reply":"2023-07-21T15:59:58.986609Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Above is the generator function! This function downsamples and then upsamples input images. Skip connections are used in the upsample stage in order to avoid and remedy the vanishing gradient problem. Overall, the generator will work to produce images that the discriminator will classify as real or generated.","metadata":{}},{"cell_type":"markdown","source":"<a id=\"disc\"></a>\n# **Building the Discriminator**","metadata":{}},{"cell_type":"code","source":"# Creating the Discriminator! \ndef Discriminator():\n    initializer = tf.random_normal_initializer(0., 0.02)\n    gamma_init = keras.initializers.RandomNormal(mean=0.0, stddev=0.02)\n\n    inp = layers.Input(shape=[256, 256, 3], name='input_image')\n\n    x = inp\n\n    down1 = downsample(64, 4, False)(x) # (bs, 128, 128, 64)\n    down2 = downsample(128, 4)(down1) # (bs, 64, 64, 128)\n    down3 = downsample(256, 4)(down2) # (bs, 32, 32, 256)\n\n    zero_pad1 = layers.ZeroPadding2D()(down3) # (bs, 34, 34, 256)\n    conv = layers.Conv2D(512, 4, strides=1,\n                         kernel_initializer=initializer,\n                         use_bias=False)(zero_pad1) # (bs, 31, 31, 512)\n\n    norm1 = tfa.layers.InstanceNormalization(gamma_initializer=gamma_init)(conv)\n\n    leaky_relu = layers.LeakyReLU()(norm1)\n\n    zero_pad2 = layers.ZeroPadding2D()(leaky_relu) # (bs, 33, 33, 512)\n\n    last = layers.Conv2D(1, 4, strides=1,\n                         kernel_initializer=initializer)(zero_pad2) # (bs, 30, 30, 1)\n\n    return tf.keras.Model(inputs=inp, outputs=last)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:58.988754Z","iopub.execute_input":"2023-07-21T15:59:58.989746Z","iopub.status.idle":"2023-07-21T15:59:59.004337Z","shell.execute_reply.started":"2023-07-21T15:59:58.989714Z","shell.execute_reply":"2023-07-21T15:59:59.003231Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The discriminator above takes an image created from the generator and determines whether or not the image is real or fake. The output here is another image. If the image has higher pixel values, then the discriminator has determined the input to be real. If the image has lower pixel values, then the input image is determined to be fake. ","metadata":{}},{"cell_type":"code","source":"# Adding to distribution strategies\nwith strategy.scope():\n    monet_generator = Generator() \n    photo_generator = Generator() \n\n    monet_discriminator = Discriminator() \n    photo_discriminator = Discriminator() ","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:59:59.005521Z","iopub.execute_input":"2023-07-21T15:59:59.006589Z","iopub.status.idle":"2023-07-21T16:00:02.252179Z","shell.execute_reply.started":"2023-07-21T15:59:59.006558Z","shell.execute_reply":"2023-07-21T16:00:02.251015Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The code chunk above does the following:\n- monet_generator: This transforms photos into Monet style paintings\n- photo_generator: This works backwards. It transforms Monet paintings into regular photos.\n- monet_discriminator: This determines whether or not an image is a real Monet painting or a generated painting.\n- photo_discriminator: This determines whether or not an image is a real photo or a generated photo.","metadata":{}},{"cell_type":"markdown","source":"<a id=\"gan\"></a>\n# **Building CycleGAN**","metadata":{}},{"cell_type":"code","source":"# Creating CycleGan class\nclass CycleGan(keras.Model):\n    def __init__(\n        self,\n        monet_generator,\n        photo_generator,\n        monet_discriminator,\n        photo_discriminator,\n        lambda_cycle=10,\n    ):\n        super(CycleGan, self).__init__()\n        self.m_gen = monet_generator\n        self.p_gen = photo_generator\n        self.m_disc = monet_discriminator\n        self.p_disc = photo_discriminator\n        self.lambda_cycle = lambda_cycle\n        \n    def compile(\n        self,\n        m_gen_optimizer,\n        p_gen_optimizer,\n        m_disc_optimizer,\n        p_disc_optimizer,\n        gen_loss_fn,\n        disc_loss_fn,\n        cycle_loss_fn,\n        identity_loss_fn\n    ):\n        super(CycleGan, self).compile()\n        self.m_gen_optimizer = m_gen_optimizer\n        self.p_gen_optimizer = p_gen_optimizer\n        self.m_disc_optimizer = m_disc_optimizer\n        self.p_disc_optimizer = p_disc_optimizer\n        self.gen_loss_fn = gen_loss_fn\n        self.disc_loss_fn = disc_loss_fn\n        self.cycle_loss_fn = cycle_loss_fn\n        self.identity_loss_fn = identity_loss_fn\n        \n    def train_step(self, batch_data):\n        real_monet, real_photo = batch_data\n        \n        with tf.GradientTape(persistent=True) as tape:\n            # photo to monet back to photo\n            fake_monet = self.m_gen(real_photo, training=True)\n            cycled_photo = self.p_gen(fake_monet, training=True)\n\n            # monet to photo back to monet\n            fake_photo = self.p_gen(real_monet, training=True)\n            cycled_monet = self.m_gen(fake_photo, training=True)\n\n            # generating itself\n            same_monet = self.m_gen(real_monet, training=True)\n            same_photo = self.p_gen(real_photo, training=True)\n\n            # discriminator used to check, inputing real images\n            disc_real_monet = self.m_disc(real_monet, training=True)\n            disc_real_photo = self.p_disc(real_photo, training=True)\n\n            # discriminator used to check, inputing fake images\n            disc_fake_monet = self.m_disc(fake_monet, training=True)\n            disc_fake_photo = self.p_disc(fake_photo, training=True)\n\n            # evaluates generator loss\n            monet_gen_loss = self.gen_loss_fn(disc_fake_monet)\n            photo_gen_loss = self.gen_loss_fn(disc_fake_photo)\n\n            # evaluates total cycle consistency loss\n            total_cycle_loss = self.cycle_loss_fn(real_monet, cycled_monet, self.lambda_cycle) + self.cycle_loss_fn(real_photo, cycled_photo, self.lambda_cycle)\n\n            # evaluates total generator loss\n            total_monet_gen_loss = monet_gen_loss + total_cycle_loss + self.identity_loss_fn(real_monet, same_monet, self.lambda_cycle)\n            total_photo_gen_loss = photo_gen_loss + total_cycle_loss + self.identity_loss_fn(real_photo, same_photo, self.lambda_cycle)\n\n            # evaluates discriminator loss\n            monet_disc_loss = self.disc_loss_fn(disc_real_monet, disc_fake_monet)\n            photo_disc_loss = self.disc_loss_fn(disc_real_photo, disc_fake_photo)\n            \n         # Calculate the gradients for generator and discriminator\n        monet_generator_gradients = tape.gradient(total_monet_gen_loss,\n                                                  self.m_gen.trainable_variables)\n        photo_generator_gradients = tape.gradient(total_photo_gen_loss,\n                                                  self.p_gen.trainable_variables)\n\n        monet_discriminator_gradients = tape.gradient(monet_disc_loss,\n                                                      self.m_disc.trainable_variables)\n        photo_discriminator_gradients = tape.gradient(photo_disc_loss,\n                                                      self.p_disc.trainable_variables)\n\n        # Apply the gradients to the optimizer\n        self.m_gen_optimizer.apply_gradients(zip(monet_generator_gradients,\n                                                 self.m_gen.trainable_variables))\n\n        self.p_gen_optimizer.apply_gradients(zip(photo_generator_gradients,\n                                                 self.p_gen.trainable_variables))\n\n        self.m_disc_optimizer.apply_gradients(zip(monet_discriminator_gradients,\n                                                  self.m_disc.trainable_variables))\n\n        self.p_disc_optimizer.apply_gradients(zip(photo_discriminator_gradients,\n                                                  self.p_disc.trainable_variables))\n        \n        return {\n            \"monet_gen_loss\": total_monet_gen_loss,\n            \"photo_gen_loss\": total_photo_gen_loss,\n            \"monet_disc_loss\": monet_disc_loss,\n            \"photo_disc_loss\": photo_disc_loss\n        }","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:00:02.253953Z","iopub.execute_input":"2023-07-21T16:00:02.254317Z","iopub.status.idle":"2023-07-21T16:00:02.279250Z","shell.execute_reply.started":"2023-07-21T16:00:02.254282Z","shell.execute_reply":"2023-07-21T16:00:02.277905Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"loss\"></a>\n# **Defining Loss Functions**","metadata":{}},{"cell_type":"code","source":"# Adding to distribution strategies\nwith strategy.scope():\n    def discriminator_loss(real, generated):\n        real_loss = tf.keras.losses.BinaryCrossentropy(from_logits=True, reduction=tf.keras.losses.Reduction.NONE)(tf.ones_like(real), real)\n        generated_loss = tf.keras.losses.BinaryCrossentropy(from_logits=True, reduction=tf.keras.losses.Reduction.NONE)(tf.zeros_like(generated), generated)\n        total_disc_loss = real_loss + generated_loss\n        return total_disc_loss * 0.5","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:00:02.281510Z","iopub.execute_input":"2023-07-21T16:00:02.281965Z","iopub.status.idle":"2023-07-21T16:00:02.291842Z","shell.execute_reply.started":"2023-07-21T16:00:02.281927Z","shell.execute_reply":"2023-07-21T16:00:02.290643Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    def generator_loss(generated):\n        return tf.keras.losses.BinaryCrossentropy(from_logits=True, reduction=tf.keras.losses.Reduction.NONE)(tf.ones_like(generated), generated)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:00:02.293346Z","iopub.execute_input":"2023-07-21T16:00:02.294446Z","iopub.status.idle":"2023-07-21T16:00:02.309255Z","shell.execute_reply.started":"2023-07-21T16:00:02.294404Z","shell.execute_reply":"2023-07-21T16:00:02.308078Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    def calc_cycle_loss(real_image, cycled_image, LAMBDA):\n        loss1 = tf.reduce_mean(tf.abs(real_image - cycled_image))\n        return LAMBDA * loss1","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:00:02.311052Z","iopub.execute_input":"2023-07-21T16:00:02.311511Z","iopub.status.idle":"2023-07-21T16:00:02.322503Z","shell.execute_reply.started":"2023-07-21T16:00:02.311470Z","shell.execute_reply":"2023-07-21T16:00:02.321150Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    def identity_loss(real_image, same_image, LAMBDA):\n        loss = tf.reduce_mean(tf.abs(real_image - same_image))\n        return LAMBDA * 0.5 * loss","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:00:02.325323Z","iopub.execute_input":"2023-07-21T16:00:02.326079Z","iopub.status.idle":"2023-07-21T16:00:02.337426Z","shell.execute_reply.started":"2023-07-21T16:00:02.326041Z","shell.execute_reply":"2023-07-21T16:00:02.336370Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"model\"></a>\n# **Training the Model**","metadata":{}},{"cell_type":"code","source":"# Adding to distribution strategies\nwith strategy.scope():\n    monet_generator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n    photo_generator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n\n    monet_discriminator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)\n    photo_discriminator_optimizer = tf.keras.optimizers.Adam(2e-4, beta_1=0.5)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:00:02.340039Z","iopub.execute_input":"2023-07-21T16:00:02.340405Z","iopub.status.idle":"2023-07-21T16:00:02.361633Z","shell.execute_reply.started":"2023-07-21T16:00:02.340356Z","shell.execute_reply":"2023-07-21T16:00:02.360218Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n    cycle_gan_model = CycleGan(\n        monet_generator, photo_generator, monet_discriminator, photo_discriminator\n    )\n\n    cycle_gan_model.compile(\n        m_gen_optimizer = monet_generator_optimizer,\n        p_gen_optimizer = photo_generator_optimizer,\n        m_disc_optimizer = monet_discriminator_optimizer,\n        p_disc_optimizer = photo_discriminator_optimizer,\n        gen_loss_fn = generator_loss,\n        disc_loss_fn = discriminator_loss,\n        cycle_loss_fn = calc_cycle_loss,\n        identity_loss_fn = identity_loss\n    )","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:00:20.831265Z","iopub.execute_input":"2023-07-21T16:00:20.831625Z","iopub.status.idle":"2023-07-21T16:00:20.857315Z","shell.execute_reply.started":"2023-07-21T16:00:20.831597Z","shell.execute_reply":"2023-07-21T16:00:20.856330Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Fitting the model!\ncycle_gan_model.fit(\n    tf.data.Dataset.zip((monet_ds, photo_ds)),\n    epochs=25\n)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:00:23.460281Z","iopub.execute_input":"2023-07-21T16:00:23.460649Z","iopub.status.idle":"2023-07-21T16:34:40.243835Z","shell.execute_reply.started":"2023-07-21T16:00:23.460620Z","shell.execute_reply":"2023-07-21T16:34:40.242709Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"results\"></a>\n# **Results**","metadata":{}},{"cell_type":"markdown","source":"Below are the best results yielded from the CycleGAN model:\n\n- monet_gen_loss: 2.6839, epoch=25\n- photo_gen_loss: 2.7724, epoch=25\n- monet_disc_loss: 0.6129, epoch=13\n- photo_disc_loss: 0.5300, epoch=3\n\nFrom the information above, it can be argued that the generator of the CycleGAN model performed best at the highest number of epochs (25). In contrast, the discriminator tended to perform better at earlier epochs. ","metadata":{}},{"cell_type":"code","source":"# Visualizing the new images in Monet style\n_, ax = plt.subplots(5, 2, figsize=(12, 12))\nfor i, img in enumerate(photo_ds.take(5)):\n    prediction = monet_generator(img, training=False)[0].numpy()\n    prediction = (prediction * 127.5 + 127.5).astype(np.uint8)\n    img = (img[0] * 127.5 + 127.5).numpy().astype(np.uint8)\n\n    ax[i, 0].imshow(img)\n    ax[i, 1].imshow(prediction)\n    ax[i, 0].set_title(\"Input Photo\")\n    ax[i, 1].set_title(\"Monet Style Output\")\n    ax[i, 0].axis(\"off\")\n    ax[i, 1].axis(\"off\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:45:32.697321Z","iopub.execute_input":"2023-07-21T16:45:32.698281Z","iopub.status.idle":"2023-07-21T16:45:34.851426Z","shell.execute_reply.started":"2023-07-21T16:45:32.698202Z","shell.execute_reply":"2023-07-21T16:45:34.850243Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Above, we can see examples of input photos and their Monet style outputs. Overall, the output images obtain the softer resolution that appears to resemble a Monet painting. In my opinion, the best looking example here is the one of the water under the bridge:\n\n![Screen Shot 2023-07-21 at 12.48.27 PM.png](attachment:97fe2c2d-e3c9-4efb-b4f8-4a970d8de025.png)\n\nHere, you can see that the image lacks the resolution that would obviously make it a real photo. A blending of the colors and borders of objects definitely makes this appear closer to a Monet painting. In contrast, the photo below appears to not have experienced much change:\n\n![Screen Shot 2023-07-21 at 12.51.18 PM.png](attachment:e9eb1d2d-6c5d-4ae1-a674-a8900ca969c8.png)\n\nThis may be due to the fact that the input photo had less variation in its palette. In other words, the pale blue sky and sand makes the image more monochrome and thus the resulting Monet style painting is unable to take advantage of blending various shapes and colors together. ","metadata":{},"attachments":{"97fe2c2d-e3c9-4efb-b4f8-4a970d8de025.png":{"image/png":"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"},"e9eb1d2d-6c5d-4ae1-a674-a8900ca969c8.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"<a id=\"sub\"></a>\n# **Submission**","metadata":{}},{"cell_type":"code","source":"import PIL\n! mkdir ../images","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:54:24.478478Z","iopub.execute_input":"2023-07-21T16:54:24.479364Z","iopub.status.idle":"2023-07-21T16:54:25.517714Z","shell.execute_reply.started":"2023-07-21T16:54:24.479325Z","shell.execute_reply":"2023-07-21T16:54:25.516186Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"i = 1\nfor img in photo_ds:\n    prediction = monet_generator(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","metadata":{"execution":{"iopub.status.busy":"2023-07-21T16:54:34.053184Z","iopub.execute_input":"2023-07-21T16:54:34.053715Z","iopub.status.idle":"2023-07-21T17:03:55.995152Z","shell.execute_reply.started":"2023-07-21T16:54:34.053673Z","shell.execute_reply":"2023-07-21T17:03:55.994018Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import shutil\nshutil.make_archive(\"/kaggle/working/images\", 'zip', \"/kaggle/images\")","metadata":{"execution":{"iopub.status.busy":"2023-07-21T17:04:42.328642Z","iopub.execute_input":"2023-07-21T17:04:42.329007Z","iopub.status.idle":"2023-07-21T17:04:46.528086Z","shell.execute_reply.started":"2023-07-21T17:04:42.328976Z","shell.execute_reply":"2023-07-21T17:04:46.527132Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"conclusion\"></a>\n# **Conclusion**","metadata":{}},{"cell_type":"markdown","source":"By employing the use of CycleGAN, I was able to convert photos into Monet style paintings. When training the CycleGAN model, 25 epochs were used. In general, the loss of the generator portion of the model tended to improve across epochs and was the lowest at the 25th epoch. In contrast to this, the loss of the discriminator tended to fluctuate across epochs and was actually lowest at lower epochs. Future iterations of this project could employ a higher number of epochs, such as 30. It is likely that the loss from the generator would continue to decrease but the loss from the discriminator would likely fluctuate and even increase.\n\nThank you for taking the time to view my project. Please feel free to leave a like! ","metadata":{}},{"cell_type":"markdown","source":"<a id=\"ref\"></a>\n# **References**","metadata":{}},{"cell_type":"markdown","source":"- https://www.kaggle.com/competitions/gan-getting-started\n- https://www.tensorflow.org/tutorials/generative/cyclegan\n- https://www.kaggle.com/code/ruchi798/getting-started-with-gans\n- https://www.kaggle.com/code/doanquanvietnamca/the-beauty-of-cyclegan/notebook\n- https://www.kaggle.com/code/amyjang/monet-cyclegan-tutorial","metadata":{}}]}