{"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":"### Introduction\n\n","metadata":{"id":"L1x1o6RMLiZ8"}},{"cell_type":"markdown","source":"Welcome to you for this Cycle GAN kernel. Coded by me Sémi Ben Hsan (SBH) .Machine Learning Intern at TalTech - Tallinn University of Technology . This kernel includes and advanced implementation of Cycle GAN with some visuals and tricks to improve the model performance , programmed in a professional way ( The SBH style ) and explained in detail . I am waiting for your votes, opinions and comments ... If you use parts of this notebook in your scripts/notebooks, giving some kind of credit would be very much appreciated :) You can for instance link back to this notebook. Thanks!\n","metadata":{"id":"m-xc-ersKzG-"}},{"cell_type":"markdown","source":"### Plan","metadata":{"id":"Ac5uUUYwNHw-"}},{"cell_type":"markdown","source":"0. Importations\n1. Redefining Dataset\n2. Generator Architecture\n3. Model Blocks\n4. Full Generator\n5. Discriminator Architecture\n6.  Discriminator Code\n7. Discriminator Loss\n8. Generator Loss\n\n  8.1 Adversarial Loss\n\n  8.2 Identity loss\n\n  8.3 Cycle Consistency Loss\n\n  8.4 Full Generator Loss\n\n9. CycleGAN Training\n10. Main \n\n  10.1 Loading Data\n\n  10.2 Visuals\n\n  10.3.Prepare Model\n11. Tricks And improvements","metadata":{"id":"6yS0uVi_Oasf"}},{"cell_type":"markdown","source":"### 0. IMPORTATIONS","metadata":{"id":"SecMFqz9GKiC"}},{"cell_type":"code","source":"import glob\nimport random\nimport os\nfrom PIL import Image\nimport torch\nfrom torch import nn\nfrom tqdm.auto import tqdm\nfrom torchvision import transforms\nfrom torchvision.utils import make_grid\nfrom torch.utils.data import Dataset\nfrom torch.utils.data import DataLoader\nimport matplotlib.pyplot as plt\ntorch.manual_seed(0)","metadata":{"papermill":{"duration":1.318295,"end_time":"2021-06-04T20:54:11.481174","exception":false,"start_time":"2021-06-04T20:54:10.162879","status":"completed"},"tags":[],"id":"comparative-doubt","outputId":"90d306f4-2bfe-49eb-bca4-2cf48e77be9b","execution":{"iopub.status.busy":"2021-06-05T08:42:37.602089Z","iopub.execute_input":"2021-06-05T08:42:37.602999Z","iopub.status.idle":"2021-06-05T08:42:37.612078Z","shell.execute_reply.started":"2021-06-05T08:42:37.602960Z","shell.execute_reply":"2021-06-05T08:42:37.611198Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 1. Redefining Dataset","metadata":{"id":"l1bfgpvcGQNP"}},{"cell_type":"markdown","source":"PyTorch supports two classes, which are torch.utils.data.Dataset and torch.utils.data.DataLoader, to facilitate loading dataset and to make mini-batch without large effort. Let's use them now as below  in order to load our Monet and Real Photos ","metadata":{"id":"IIU1ugZoHKsA"}},{"cell_type":"code","source":"class ImageDataset(Dataset):\n    def __init__(self,MONET_FILENAMES,PHOTO_FILENAMES, transform=None): \n        self.transform = transform\n        self.PHOTO_FILENAMES = PHOTO_FILENAMES\n        self.MONET_FILENAMES = MONET_FILENAMES\n        if len(self.MONET_FILENAMES) > len (self.PHOTO_FILENAMES):\n            self.MONET_FILENAMES, self.PHOTO_FILENAMES = self.PHOTO_FILENAMES, self.MONET_FILENAMES\n        self.new_perm()\n\n    def new_perm(self):\n        self.randperm = torch.randperm(len(self.PHOTO_FILENAMES))[:len(self.MONET_FILENAMES)]\n    def __getitem__(self, index):     \n        item_MONET_FILENAMES = self.transform(Image.open(self.MONET_FILENAMES[index % len(self.MONET_FILENAMES)]))\n        item_PHOTO_FILENAMES = self.transform(Image.open(self.PHOTO_FILENAMES[self.randperm[index]]))\n        if item_MONET_FILENAMES.shape[0] != 3: \n            item_MONET_FILENAMES = item_MONET_FILENAMES.repeat(3, 1, 1)\n        if item_PHOTO_FILENAMES.shape[0] != 3: \n            item_PHOTO_FILENAMES = item_PHOTO_FILENAMES.repeat(3, 1, 1)\n        if index == len(self) - 1:\n            self.new_perm()\n        return (item_MONET_FILENAMES - 0.5) * 2, (item_PHOTO_FILENAMES - 0.5) * 2\n\n    def __len__(self):\n        return min(len(self.MONET_FILENAMES), len(self.PHOTO_FILENAMES))","metadata":{"papermill":{"duration":0.037301,"end_time":"2021-06-04T20:54:11.542569","exception":false,"start_time":"2021-06-04T20:54:11.505268","status":"completed"},"tags":[],"id":"statutory-organizer","execution":{"iopub.status.busy":"2021-06-05T08:42:37.613852Z","iopub.execute_input":"2021-06-05T08:42:37.614474Z","iopub.status.idle":"2021-06-05T08:42:37.625649Z","shell.execute_reply.started":"2021-06-05T08:42:37.614429Z","shell.execute_reply":"2021-06-05T08:42:37.624571Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 2. Generator Architecture ","metadata":{"id":"liM0Xyw7IYQV"}},{"cell_type":"markdown","source":"\nThe generator is responsible for generating images from a specific domain. CycleGAN architecture has two generators, in this context we will have one generator that will take photos and generate Monet paints, and the other generator will take Monet paintings and generate photos.\n\nBellow, we have the architecture of the original CycleGAN generator , ours have some changes to improve performance on this task.\n","metadata":{"id":"ATkaJrfSIeE3"}},{"cell_type":"markdown","source":"Diagram of a CycleGAN generator: composed of encoding blocks, residual blocks, and then decoding blocks.","metadata":{"id":"B3_sbC2BIeLH"}},{"cell_type":"markdown","source":"![Cycle Gan.PNG](data:image/png;base64,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)","metadata":{"id":"j0jcTiDZH0aI"}},{"cell_type":"markdown","source":"### 3 . Model Blocks","metadata":{"id":"D9bXFzDyKqMB"}},{"cell_type":"markdown","source":"\nHere we the building blocks of our models:\n\nContractingBlock (Encoder) block: Apply convolutional filters while also reducing data resolution and increasing features.\n\nExpanding (Decoder) block: Apply convolutional filters while also increasing data resolution and decreasing features.\n\nResidual block: Apply convolutional filters to find relevant data patterns and keeps features constant. We will use here some skip connections in order to get Residual blocks\n\nLet's go to the implementation .... \nFeel free to ask about any line of code","metadata":{"id":"qT3AgCmWJTJr"}},{"cell_type":"code","source":"class ResidualBlock(nn.Module): \n    def __init__(self, input_channels):\n        super(ResidualBlock, self).__init__()\n        self.conv1 = nn.Conv2d(input_channels, input_channels, kernel_size=3, padding=1, padding_mode='reflect')\n        self.conv2 = nn.Conv2d(input_channels, input_channels, kernel_size=3, padding=1, padding_mode='reflect')\n        self.instancenorm = nn.InstanceNorm2d(input_channels)\n        self.activation = nn.ReLU()\n\n    def forward(self, x):\n        original_x = x.clone()\n        x = self.conv1(x)\n        x = self.instancenorm(x)\n        x = self.activation(x)\n        x = self.conv2(x)\n        x = self.instancenorm(x)\n        return original_x + x","metadata":{"papermill":{"duration":0.035359,"end_time":"2021-06-04T20:54:11.602785","exception":false,"start_time":"2021-06-04T20:54:11.567426","status":"completed"},"tags":[],"id":"recovered-conditions","execution":{"iopub.status.busy":"2021-06-05T08:42:37.641348Z","iopub.execute_input":"2021-06-05T08:42:37.642124Z","iopub.status.idle":"2021-06-05T08:42:37.649722Z","shell.execute_reply.started":"2021-06-05T08:42:37.642075Z","shell.execute_reply":"2021-06-05T08:42:37.648625Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class ContractingBlock(nn.Module): \n    def __init__(self, input_channels, use_bn=True, kernel_size=3, activation='relu'):\n        super(ContractingBlock, self).__init__()\n        self.conv1 = nn.Conv2d(input_channels, input_channels * 2, kernel_size=kernel_size, padding=1, stride=2, padding_mode='reflect')\n        self.activation = nn.ReLU() if activation == 'relu' else nn.LeakyReLU(0.2)\n        if use_bn:\n            self.instancenorm = nn.InstanceNorm2d(input_channels * 2)\n        self.use_bn = use_bn\n\n    def forward(self, x):\n        x = self.conv1(x)\n        if self.use_bn:\n            x = self.instancenorm(x)\n        x = self.activation(x)\n        return x\n\nclass ExpandingBlock(nn.Module):\n\n    def __init__(self, input_channels, use_bn=True):\n        super(ExpandingBlock, self).__init__()\n        self.conv1 = nn.ConvTranspose2d(input_channels, input_channels // 2, kernel_size=3, stride=2, padding=1, output_padding=1)\n        if use_bn:\n            self.instancenorm = nn.InstanceNorm2d(input_channels // 2)\n        self.use_bn = use_bn\n        self.activation = nn.ReLU()\n\n    def forward(self, x):\n        x = self.conv1(x)\n        if self.use_bn:\n            x = self.instancenorm(x)\n        x = self.activation(x)\n        return x","metadata":{"papermill":{"duration":0.051839,"end_time":"2021-06-04T20:54:11.689927","exception":false,"start_time":"2021-06-04T20:54:11.638088","status":"completed"},"tags":[],"id":"statistical-control","execution":{"iopub.status.busy":"2021-06-05T08:42:37.669424Z","iopub.execute_input":"2021-06-05T08:42:37.669794Z","iopub.status.idle":"2021-06-05T08:42:37.681024Z","shell.execute_reply.started":"2021-06-05T08:42:37.669759Z","shell.execute_reply":"2021-06-05T08:42:37.679931Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This layer will be on the top and in the final layers of the models .. It's role is to map the input matrix to desired output channels","metadata":{"id":"dhvXfFN0KU6b"}},{"cell_type":"code","source":"class FeatureMapBlock(nn.Module):\n    def __init__(self, input_channels, output_channels):\n        super(FeatureMapBlock, self).__init__()\n        self.conv = nn.Conv2d(input_channels, output_channels, kernel_size=7, padding=3, padding_mode='reflect')\n\n    def forward(self, x):\n        x = self.conv(x)\n        return x","metadata":{"papermill":{"duration":0.043934,"end_time":"2021-06-04T20:54:11.769461","exception":false,"start_time":"2021-06-04T20:54:11.725527","status":"completed"},"tags":[],"id":"labeled-fossil","execution":{"iopub.status.busy":"2021-06-05T08:42:37.701570Z","iopub.execute_input":"2021-06-05T08:42:37.702019Z","iopub.status.idle":"2021-06-05T08:42:37.711317Z","shell.execute_reply.started":"2021-06-05T08:42:37.701979Z","shell.execute_reply":"2021-06-05T08:42:37.710000Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 4 . Full Generator","metadata":{"id":"m8TE1a4vKuKX"}},{"cell_type":"code","source":"class Generator(nn.Module):\n    def __init__(self, input_channels, output_channels, hidden_channels=64):\n        super(Generator, self).__init__()\n        self.upfeature = FeatureMapBlock(input_channels, hidden_channels)\n        self.contract1 = ContractingBlock(hidden_channels)\n        self.contract2 = ContractingBlock(hidden_channels * 2)\n        res_mult = 4\n        self.res0 = ResidualBlock(hidden_channels * res_mult)\n        self.res1 = ResidualBlock(hidden_channels * res_mult)\n        self.res2 = ResidualBlock(hidden_channels * res_mult)\n        self.res3 = ResidualBlock(hidden_channels * res_mult)\n        self.res4 = ResidualBlock(hidden_channels * res_mult)\n        self.res5 = ResidualBlock(hidden_channels * res_mult)\n        self.res6 = ResidualBlock(hidden_channels * res_mult)\n        self.res7 = ResidualBlock(hidden_channels * res_mult)\n        self.res8 = ResidualBlock(hidden_channels * res_mult)\n        self.expand2 = ExpandingBlock(hidden_channels * 4)\n        self.expand3 = ExpandingBlock(hidden_channels * 2)\n        self.downfeature = FeatureMapBlock(hidden_channels, output_channels)\n        self.tanh = torch.nn.Tanh()\n\n    def forward(self, x):\n        x0 = self.upfeature(x)\n        x1 = self.contract1(x0)\n        x2 = self.contract2(x1)\n        x3 = self.res0(x2)\n        x4 = self.res1(x3)\n        x5 = self.res2(x4)\n        x6 = self.res3(x5)\n        x7 = self.res4(x6)\n        x8 = self.res5(x7)\n        x9 = self.res6(x8)\n        x10 = self.res7(x9)\n        x11 = self.res8(x10)\n        x12 = self.expand2(x11)\n        x13 = self.expand3(x12)\n        xn = self.downfeature(x13)\n        return self.tanh(xn)","metadata":{"papermill":{"duration":0.052104,"end_time":"2021-06-04T20:54:11.857116","exception":false,"start_time":"2021-06-04T20:54:11.805012","status":"completed"},"tags":[],"id":"international-audio","execution":{"iopub.status.busy":"2021-06-05T08:42:37.719769Z","iopub.execute_input":"2021-06-05T08:42:37.720136Z","iopub.status.idle":"2021-06-05T08:42:37.734990Z","shell.execute_reply.started":"2021-06-05T08:42:37.720106Z","shell.execute_reply":"2021-06-05T08:42:37.733766Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 5. Discriminator Architecture","metadata":{"id":"khK0IsRmL6cf"}},{"cell_type":"markdown","source":"The discriminator is responsible for differentiating real images from images that have been generated by a generator model.\n\nBellow, we have the architecture of the original CycleGAN discriminator, again, ours have some changes to improve performance on this task.","metadata":{"id":"YB9B00MGLMzy"}},{"cell_type":"markdown","source":"![Patch GAN.PNG](data:image/png;base64,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)","metadata":{"id":"UL36hD1lLWx-"}},{"cell_type":"markdown","source":"### 6 . Discriminator Code","metadata":{"id":"X-Ztu7RYL947"}},{"cell_type":"code","source":"class Discriminator(nn.Module):\n    def __init__(self, input_channels, hidden_channels=64):\n        super(Discriminator, self).__init__()\n        self.upfeature = FeatureMapBlock(input_channels, hidden_channels)\n        self.contract1 = ContractingBlock(hidden_channels, use_bn=False, kernel_size=4, activation='lrelu')\n        self.contract2 = ContractingBlock(hidden_channels * 2, kernel_size=4, activation='lrelu')\n        self.contract3 = ContractingBlock(hidden_channels * 4, kernel_size=4, activation='lrelu')\n        self.final = nn.Conv2d(hidden_channels * 8, 1, kernel_size=1)\n\n    def forward(self, x):\n        x0 = self.upfeature(x)\n        x1 = self.contract1(x0)\n        x2 = self.contract2(x1)\n        x3 = self.contract3(x2)\n        xn = self.final(x3)\n        return xn","metadata":{"papermill":{"duration":0.046781,"end_time":"2021-06-04T20:54:11.939425","exception":false,"start_time":"2021-06-04T20:54:11.892644","status":"completed"},"tags":[],"id":"acceptable-coaching","execution":{"iopub.status.busy":"2021-06-05T08:42:37.736929Z","iopub.execute_input":"2021-06-05T08:42:37.737257Z","iopub.status.idle":"2021-06-05T08:42:37.754939Z","shell.execute_reply.started":"2021-06-05T08:42:37.737229Z","shell.execute_reply":"2021-06-05T08:42:37.754088Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 7. Discriminator Loss ","metadata":{"id":"hUlxnXumMQMc"}},{"cell_type":"markdown","source":"First, we will going to be implementing the discriminator loss ... Like a classique discriminator loss in a Simple GAN","metadata":{"id":"dE9BA9slMSFJ"}},{"cell_type":"code","source":"def get_disc_loss(real_X, fake_X, disc_X, adv_criterion):\n \n    disc_fake_X_hat = disc_X(fake_X.detach()) # Detach generator in order the fix it's params while training the discriminator\n    disc_fake_X_loss = adv_criterion(disc_fake_X_hat, torch.zeros_like(disc_fake_X_hat))\n    disc_real_X_hat = disc_X(real_X)\n    disc_real_X_loss = adv_criterion(disc_real_X_hat, torch.ones_like(disc_real_X_hat))\n    disc_loss = (disc_fake_X_loss + disc_real_X_loss) / 2\n    return disc_loss","metadata":{"papermill":{"duration":0.043731,"end_time":"2021-06-04T20:54:12.018287","exception":false,"start_time":"2021-06-04T20:54:11.974556","status":"completed"},"tags":[],"id":"featured-cement","execution":{"iopub.status.busy":"2021-06-05T08:42:37.756728Z","iopub.execute_input":"2021-06-05T08:42:37.757214Z","iopub.status.idle":"2021-06-05T08:42:37.773031Z","shell.execute_reply.started":"2021-06-05T08:42:37.757151Z","shell.execute_reply":"2021-06-05T08:42:37.772101Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 8 . Generator Loss","metadata":{"id":"SMa7dfwXDFLX"}},{"cell_type":"markdown","source":"8.1  Adversarial Loss","metadata":{"id":"2So8e2bpDoYW"}},{"cell_type":"markdown","source":"The first component of the generator's loss I'm going to implement is its adversarial loss ","metadata":{"id":"H0iHL3kuDsOH"}},{"cell_type":"code","source":"def get_gen_adversarial_loss(real_X, disc_Y, gen_XY, adv_criterion):\n    fake_Y = gen_XY(real_X)\n    disc_fake_Y_hat = disc_Y(fake_Y)\n    adversarial_loss = adv_criterion(disc_fake_Y_hat, torch.ones_like(disc_fake_Y_hat))\n    return adversarial_loss, fake_Y","metadata":{"papermill":{"duration":0.044066,"end_time":"2021-06-04T20:54:12.097542","exception":false,"start_time":"2021-06-04T20:54:12.053476","status":"completed"},"tags":[],"id":"related-economy","execution":{"iopub.status.busy":"2021-06-05T08:42:37.774851Z","iopub.execute_input":"2021-06-05T08:42:37.775348Z","iopub.status.idle":"2021-06-05T08:42:37.787507Z","shell.execute_reply.started":"2021-06-05T08:42:37.775304Z","shell.execute_reply":"2021-06-05T08:42:37.786448Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"8.2 Identity loss","metadata":{"id":"OjSF-wp_EL7i"}},{"cell_type":"markdown","source":"We'll want to measure the change in an image when you pass the generator an example from the target domain instead of the input domain it's expecting. The output should be the same as the input since it is already of the target domain class. For example, if you put a Monet Photo through a PHOTO -> MONET generator, We'll expect the output to be the same Monet PHOTO because nothing needed to be transformed. It's already a MONET PHOTO! You don't want your generator to be transforming it into any other thing, so you want to encourage this behavior. In encouraging this identity mapping, this will help also to  properly preserve the colors of an image, even when the expected input (here, a MONET PHOTO) was put in. ","metadata":{"id":"tYRJoDcNEt96"}},{"cell_type":"code","source":"def get_identity_loss(real_X, gen_YX, identity_criterion):\n    identity_X = gen_YX(real_X)\n    identity_loss = identity_criterion(identity_X, real_X)\n    return identity_loss, identity_X","metadata":{"papermill":{"duration":0.043103,"end_time":"2021-06-04T20:54:12.176522","exception":false,"start_time":"2021-06-04T20:54:12.133419","status":"completed"},"tags":[],"id":"disciplinary-specification","execution":{"iopub.status.busy":"2021-06-05T08:42:37.789088Z","iopub.execute_input":"2021-06-05T08:42:37.789758Z","iopub.status.idle":"2021-06-05T08:42:37.800690Z","shell.execute_reply.started":"2021-06-05T08:42:37.789726Z","shell.execute_reply":"2021-06-05T08:42:37.799661Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"8.3 Cycle Consistency Loss","metadata":{"id":"_kWqFS-nFd2p"}},{"cell_type":"markdown","source":"This is used to ensure that when you put an image through one generator, that if it is then transformed back into the input class using the opposite generator, the image is the same as the original input image.Since I've already generated a fake image for the adversarial part,I can now pass that fake image back to produce a full cycle—this loss will encourage the cycle to preserve as much information as possible.","metadata":{"id":"6qGrSWp1Fm9Z"}},{"cell_type":"code","source":"def get_cycle_consistency_loss(real_X, fake_Y, gen_YX, cycle_criterion):\n    cycle_X = gen_YX(fake_Y)\n    cycle_loss = cycle_criterion(cycle_X, real_X)\n    return cycle_loss, cycle_X","metadata":{"papermill":{"duration":0.043321,"end_time":"2021-06-04T20:54:12.255744","exception":false,"start_time":"2021-06-04T20:54:12.212423","status":"completed"},"tags":[],"id":"worldwide-uganda","execution":{"iopub.status.busy":"2021-06-05T08:42:37.801876Z","iopub.execute_input":"2021-06-05T08:42:37.802488Z","iopub.status.idle":"2021-06-05T08:42:37.815929Z","shell.execute_reply.started":"2021-06-05T08:42:37.802454Z","shell.execute_reply":"2021-06-05T08:42:37.815059Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"8.4 Full Generator Loss\n","metadata":{"id":"0FXa8zLnF-s1"}},{"cell_type":"markdown","source":"Finally, I can put it all together!","metadata":{"id":"AYz_R1kVGBis"}},{"cell_type":"code","source":"def get_gen_loss(real_P, real_M, gen_PM, gen_MP, disc_P, disc_M, adv_criterion, identity_criterion, cycle_criterion, lambda_identity=0.1, lambda_cycle=10):\n    \n    adv_loss_MP, fake_P = get_gen_adversarial_loss(real_M, disc_P, gen_MP, adv_criterion)\n    adv_loss_PM, fake_M = get_gen_adversarial_loss(real_P, disc_M, gen_PM, adv_criterion)\n    gen_adversarial_loss = adv_loss_MP + adv_loss_PM\n\n    identity_loss_P, identity_P = get_identity_loss(real_P, gen_MP, identity_criterion)\n    identity_loss_M, identity_M = get_identity_loss(real_M, gen_PM, identity_criterion)\n    gen_identity_loss = identity_loss_M + identity_loss_P\n\n    cycle_loss_MP, cycle_P = get_cycle_consistency_loss(real_P, fake_M, gen_MP, cycle_criterion)\n    cycle_loss_PM, cycle_M = get_cycle_consistency_loss(real_M, fake_P, gen_PM, cycle_criterion)\n    gen_cycle_loss = cycle_loss_PM + cycle_loss_PM\n\n    gen_loss = lambda_identity * gen_identity_loss + lambda_cycle * gen_cycle_loss + gen_adversarial_loss\n\n    return gen_loss, fake_P, fake_M","metadata":{"papermill":{"duration":0.04615,"end_time":"2021-06-04T20:54:12.337494","exception":false,"start_time":"2021-06-04T20:54:12.291344","status":"completed"},"tags":[],"id":"palestinian-michael","execution":{"iopub.status.busy":"2021-06-05T08:42:37.817292Z","iopub.execute_input":"2021-06-05T08:42:37.817798Z","iopub.status.idle":"2021-06-05T08:42:37.830541Z","shell.execute_reply.started":"2021-06-05T08:42:37.817753Z","shell.execute_reply":"2021-06-05T08:42:37.829415Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 9. CycleGAN Training","metadata":{"id":"bjRTl7n4GOlV"}},{"cell_type":"markdown","source":"Lastly, I can now train  the model and see some of my Monet PHOTO  and some that might not quite look like either! Note that this training will take a long time, so i will desactivate it because i have a very low computational ressources . And I can't wait kaggle TPU xD I'm a bit moody guys xD\n","metadata":{"id":"Xhm3mL3sGShJ"}},{"cell_type":"markdown","source":"In order to have a better train performance I'll introduce a learning rate scheduler the \"ReduceLROnPlateau\" scheduler. ","metadata":{"id":"b8t9eJ7TI2zD"}},{"cell_type":"code","source":"from skimage import color\nimport numpy as np\nfrom tqdm import tqdm\nplt.rcParams[\"figure.figsize\"] = (10, 10)\n\n\ndef train(save_model=False):\n    mean_generator_loss = 0\n    mean_discriminator_loss = 0\n    dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)\n    cur_step = 0\n    \n    scheduler_discP = torch.optim.lr_scheduler.ReduceLROnPlateau(disc_P_opt,factor=0.1, patience=5, \n                                                       verbose=True)\n    scheduler_discM = torch.optim.lr_scheduler.ReduceLROnPlateau(disc_M_opt,factor=0.1, patience=5, \n                                                       verbose=True)\n    scheduler_gen = torch.optim.lr_scheduler.ReduceLROnPlateau(gen_opt,factor=0.1, patience=5, \n                                                       verbose=True)\n    \n    for epoch in range(n_epochs):\n        losses_P = []\n        losses_M = []\n        losses_gen = []\n        for real_P,real_M in tqdm(dataloader):\n            real_P = nn.functional.interpolate(real_P, size=target_shape)\n            real_M = nn.functional.interpolate(real_M, size=target_shape)\n            cur_batch_size = len(real_P)\n            real_P = real_P\n            real_M = real_M\n        \n\n            ### Update discriminator A ###\n            disc_P_opt.zero_grad() # Zero out the gradient before backpropagation\n            with torch.no_grad():\n                fake_P = gen_MP(real_M)\n            disc_P_loss = get_disc_loss(real_P, fake_P, disc_P, adv_criterion)\n            disc_P_loss.backward(retain_graph=True) # Update gradients\n            disc_P_opt.step() # Update optimizer\n            losses_P.append(disc_P_loss.item())\n\n            ### Update discriminator B ###\n            disc_M_opt.zero_grad() # Zero out the gradient before backpropagation\n            with torch.no_grad():\n                fake_M = gen_PM(real_P)\n            disc_M_loss = get_disc_loss(real_M, fake_M, disc_M, adv_criterion)\n            disc_M_loss.backward(retain_graph=True) # Update gradients\n            disc_M_opt.step() # Update optimizer\n            losses_M.append(disc_M_loss.item())\n\n            ### Update generator ###\n            gen_opt.zero_grad()\n            gen_loss, fake_P, fake_M = get_gen_loss(\n                real_P, real_M, gen_PM, gen_MP, disc_P, disc_M, adv_criterion, recon_criterion, recon_criterion\n            )\n            gen_loss.backward() # Update gradients\n            gen_opt.step() # Update optimizer\n            losses_gen.append(gen_loss.item())\n        mean_loss_disc_M = sum(losses_M)/len(losses_M)\n        mean_loss_disc_P = sum(losses_P)/len(losses_P)\n        mean_loss_gen = sum(losses_gen)/len(losses_gen)\n        scheduler_discP.step(mean_loss_disc_P)\n        scheduler_discM.step(mean_loss_disc_M) \n        scheduler_gen.step(mean_loss_gen) ","metadata":{"papermill":{"duration":0.521398,"end_time":"2021-06-04T20:54:12.89454","exception":false,"start_time":"2021-06-04T20:54:12.373142","status":"completed"},"tags":[],"id":"innocent-prisoner","execution":{"iopub.status.busy":"2021-06-05T08:42:37.833167Z","iopub.execute_input":"2021-06-05T08:42:37.833553Z","iopub.status.idle":"2021-06-05T08:42:37.851106Z","shell.execute_reply.started":"2021-06-05T08:42:37.833520Z","shell.execute_reply":"2021-06-05T08:42:37.849734Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 10. Main","metadata":{"papermill":{"duration":0.035026,"end_time":"2021-06-04T20:54:12.964934","exception":false,"start_time":"2021-06-04T20:54:12.929908","status":"completed"},"tags":[],"id":"partial-antarctica"}},{"cell_type":"markdown","source":"10.1. Loading Data","metadata":{"papermill":{"duration":0.035612,"end_time":"2021-06-04T20:54:13.035842","exception":false,"start_time":"2021-06-04T20:54:13.00023","status":"completed"},"tags":[],"id":"extra-mission"}},{"cell_type":"code","source":"import os\nBASE_PATH = \"../input/gan-getting-started/\"\ndef prepare_Paths (BASE_PATH) :  # a function to prepare the path names of MONET/Real photos\n    MONET_PATH = os.path.join(BASE_PATH, \"monet_jpg\")\n    PHOTO_PATH = os.path.join(BASE_PATH, \"photo_jpg\")\n    return MONET_PATH,PHOTO_PATH","metadata":{"papermill":{"duration":0.043419,"end_time":"2021-06-04T20:54:13.114481","exception":false,"start_time":"2021-06-04T20:54:13.071062","status":"completed"},"tags":[],"id":"peaceful-irrigation","execution":{"iopub.status.busy":"2021-06-05T08:42:37.853032Z","iopub.execute_input":"2021-06-05T08:42:37.853378Z","iopub.status.idle":"2021-06-05T08:42:37.865667Z","shell.execute_reply.started":"2021-06-05T08:42:37.853346Z","shell.execute_reply":"2021-06-05T08:42:37.864455Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"MONET_PATH,PHOTO_PATH  = prepare_Paths (BASE_PATH)","metadata":{"papermill":{"duration":0.042978,"end_time":"2021-06-04T20:54:13.192876","exception":false,"start_time":"2021-06-04T20:54:13.149898","status":"completed"},"tags":[],"id":"latter-consolidation","execution":{"iopub.status.busy":"2021-06-05T08:42:37.869863Z","iopub.execute_input":"2021-06-05T08:42:37.870200Z","iopub.status.idle":"2021-06-05T08:42:37.881256Z","shell.execute_reply.started":"2021-06-05T08:42:37.870170Z","shell.execute_reply":"2021-06-05T08:42:37.880419Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def Prepare_list_names(MONET_PATH,PHOTO_PATH) :  # A function to prepare two lists of MONET PHOTO names\n    MONET_FILENAMES = sorted(glob.glob(os.path.join(str(MONET_PATH) + '/*.jpg')))\n    PHOTO_FILENAMES = sorted(glob.glob(os.path.join(str(PHOTO_PATH) + '/*.jpg')))\n    return MONET_FILENAMES,PHOTO_FILENAMES\nMONET_FILENAMES,PHOTO_FILENAMES = Prepare_list_names(MONET_PATH,PHOTO_PATH)","metadata":{"papermill":{"duration":0.214428,"end_time":"2021-06-04T20:54:13.44258","exception":false,"start_time":"2021-06-04T20:54:13.228152","status":"completed"},"tags":[],"id":"aware-truck","execution":{"iopub.status.busy":"2021-06-05T08:42:37.883310Z","iopub.execute_input":"2021-06-05T08:42:37.883789Z","iopub.status.idle":"2021-06-05T08:42:37.930929Z","shell.execute_reply.started":"2021-06-05T08:42:37.883750Z","shell.execute_reply":"2021-06-05T08:42:37.930026Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# The set of transformations to do in order to make some data augmentation to help the model avoiding the overfitting \ntarget_shape = 256\nload_shape = 286\ntransform = transforms.Compose([\n    transforms.Resize(load_shape),\n    transforms.RandomCrop(target_shape),\n    transforms.RandomHorizontalFlip(),\n    transforms.ToTensor(),\n])\n\nimport torchvision\ndataset = ImageDataset(MONET_FILENAMES,PHOTO_FILENAMES, transform=transform)","metadata":{"papermill":{"duration":0.101024,"end_time":"2021-06-04T20:54:13.578952","exception":false,"start_time":"2021-06-04T20:54:13.477928","status":"completed"},"tags":[],"id":"unlikely-luxury","outputId":"cd8486e1-abd9-4128-9ed6-4de639a55bd3","execution":{"iopub.status.busy":"2021-06-05T08:42:37.932936Z","iopub.execute_input":"2021-06-05T08:42:37.933549Z","iopub.status.idle":"2021-06-05T08:42:37.965160Z","shell.execute_reply.started":"2021-06-05T08:42:37.933505Z","shell.execute_reply":"2021-06-05T08:42:37.964020Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"10.2. Visuals","metadata":{"papermill":{"duration":0.035029,"end_time":"2021-06-04T20:54:13.649361","exception":false,"start_time":"2021-06-04T20:54:13.614332","status":"completed"},"tags":[],"id":"desirable-biotechnology"}},{"cell_type":"code","source":"import cv2\ndef print_folder_statistics(path): # a function to make some stats on the folder of images \n    d_image_sizes = {} \n    for image_name in os.listdir(path):\n        image = cv2.imread(os.path.join(path, image_name))\n        d_image_sizes[image.shape] = d_image_sizes.get(image.shape, 0) + 1 \n    for size, count in d_image_sizes.items(): \n        print(f\"shape: {size}\\tcount: {count}\")\n\n\nprint(f\"Monet images:\")\nprint_folder_statistics(MONET_PATH)\nprint(\"-\" * 10)\nprint(f\"Photo images:\")\nprint_folder_statistics(PHOTO_PATH)\nprint(\"-\" * 10)","metadata":{"papermill":{"duration":62.819019,"end_time":"2021-06-04T20:55:16.503622","exception":false,"start_time":"2021-06-04T20:54:13.684603","status":"completed"},"tags":[],"id":"according-operator","outputId":"fdb7cc45-a855-44c1-ad9a-b9a8b0800168","execution":{"iopub.status.busy":"2021-06-05T08:42:37.967366Z","iopub.execute_input":"2021-06-05T08:42:37.967786Z","iopub.status.idle":"2021-06-05T08:42:58.365375Z","shell.execute_reply.started":"2021-06-05T08:42:37.967745Z","shell.execute_reply":"2021-06-05T08:42:58.363607Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import math\ndef batch_visualization(path, n_images, is_random=True, figsize=(16, 16)):\n  # a function to visualize the batch of images ... Is_random param to choose weather to plot a random image or not\n    plt.figure(figsize=figsize) \n    \n    w = int(n_images ** .5) \n    h = math.ceil(n_images / w)\n    \n    all_names = os.listdir(path) \n    \n    image_names = all_names[:n_images] \n    if is_random:\n        image_names = random.sample(all_names, n_images)\n    \n    for ind, image_name in enumerate(image_names):\n        img = cv2.imread(os.path.join(path, image_name)) \n        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  \n        plt.subplot(h, w, ind + 1)\n        plt.imshow(img)\n        plt.axis(\"off\")\n    \n    plt.show()","metadata":{"papermill":{"duration":0.045889,"end_time":"2021-06-04T20:55:16.587145","exception":false,"start_time":"2021-06-04T20:55:16.541256","status":"completed"},"tags":[],"id":"manufactured-music","execution":{"iopub.status.busy":"2021-06-05T08:42:58.366654Z","iopub.status.idle":"2021-06-05T08:42:58.367150Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"batch_visualization(MONET_PATH, 1, is_random=True, figsize=(5, 5))\n","metadata":{"papermill":{"duration":0.176321,"end_time":"2021-06-04T20:55:16.788119","exception":false,"start_time":"2021-06-04T20:55:16.611798","status":"completed"},"tags":[],"id":"polished-drain","outputId":"b47eb5d6-9580-4766-d5d2-a7247b214eb6","execution":{"iopub.status.busy":"2021-06-05T08:42:58.368109Z","iopub.status.idle":"2021-06-05T08:42:58.368565Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def color_hist_visualization(image_path, figsize=(16, 4)):\n  # a function to plot an image with the histogram of it's RGB colors \n    plt.figure(figsize=figsize)\n    img = cv2.imread(image_path) \n    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) \n    plt.subplot(1, 4, 1)\n    plt.imshow(img)\n    plt.axis(\"off\")\n    \n    colors = [\"red\", \"green\", \"blue\"]\n    for i in range(len(colors)):\n        plt.subplot(1, 4, i + 2) \n        plt.hist(\n            img[:, :, i].reshape(-1),  \n            bins=25,\n            alpha=0.5,\n            color=colors[i],\n            density=True\n        )\n        plt.xlim(0, 255)\n        plt.xticks([]) \n        plt.yticks([])\n    plt.show()","metadata":{"papermill":{"duration":0.050749,"end_time":"2021-06-04T20:55:16.880874","exception":false,"start_time":"2021-06-04T20:55:16.830125","status":"completed"},"tags":[],"id":"documentary-spotlight","execution":{"iopub.status.busy":"2021-06-05T08:42:58.369888Z","iopub.status.idle":"2021-06-05T08:42:58.370392Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img_path = '../input/gan-getting-started/monet_jpg/000c1e3bff.jpg'\ncolor_hist_visualization(img_path)\n\nimg_path = '../input/gan-getting-started/monet_jpg/05144e306f.jpg'\ncolor_hist_visualization(img_path)\n\nimg_path = '../input/gan-getting-started/monet_jpg/16dabe418c.jpg'\ncolor_hist_visualization(img_path)","metadata":{"papermill":{"duration":1.02918,"end_time":"2021-06-04T20:55:17.938379","exception":false,"start_time":"2021-06-04T20:55:16.909199","status":"completed"},"tags":[],"id":"offshore-facility","outputId":"1da3b135-ecd0-4834-d88a-c650087fe245","execution":{"iopub.status.busy":"2021-06-05T08:42:58.372017Z","iopub.status.idle":"2021-06-05T08:42:58.372545Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"10.3.Prepare Model","metadata":{"papermill":{"duration":0.035289,"end_time":"2021-06-04T20:55:18.009715","exception":false,"start_time":"2021-06-04T20:55:17.974426","status":"completed"},"tags":[],"id":"digital-latest"}},{"cell_type":"markdown","source":"10.3.1 Hyperparams Tunning","metadata":{"id":"S12td0zmIiwu"}},{"cell_type":"code","source":"import torch.nn.functional as F\n\nadv_criterion = nn.MSELoss()  \nrecon_criterion = nn.L1Loss() \n\nn_epochs = 1\ndim_PHOTO = 3\ndim_MONET = 3\ndisplay_step = 200\nbatch_size = 1\nlr = 0.0002\n# device = 'cuda'","metadata":{"papermill":{"duration":0.043572,"end_time":"2021-06-04T20:55:18.089584","exception":false,"start_time":"2021-06-04T20:55:18.046012","status":"completed"},"tags":[],"id":"billion-period","execution":{"iopub.status.busy":"2021-06-05T08:42:58.373605Z","iopub.status.idle":"2021-06-05T08:42:58.374072Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"10.3.2 Creating the Generator and Discriminator and initialization","metadata":{"id":"jnh-6sv7IlmN"}},{"cell_type":"code","source":"gen_PM = Generator(dim_PHOTO, dim_MONET)\ngen_MP = Generator(dim_MONET, dim_PHOTO)\ngen_opt = torch.optim.Adam(list(gen_PM.parameters()) + list(gen_MP.parameters()), lr=lr, betas=(0.5, 0.999))\ndisc_P = Discriminator(dim_PHOTO)\ndisc_P_opt = torch.optim.Adam(disc_P.parameters(), lr=lr, betas=(0.5, 0.999))\ndisc_M = Discriminator(dim_MONET)\ndisc_M_opt = torch.optim.Adam(disc_M.parameters(), lr=lr, betas=(0.5, 0.999))\n\ndef weights_init(m): # a function to initialise the weights of our model\n    if isinstance(m, nn.Conv2d) or isinstance(m, nn.ConvTranspose2d):\n        torch.nn.init.normal_(m.weight, 0.0, 0.02)\n    if isinstance(m, nn.BatchNorm2d):\n        torch.nn.init.normal_(m.weight, 0.0, 0.02)\n        torch.nn.init.constant_(m.bias, 0)","metadata":{"papermill":{"duration":0.78065,"end_time":"2021-06-04T20:55:18.905148","exception":false,"start_time":"2021-06-04T20:55:18.124498","status":"completed"},"tags":[],"id":"delayed-principal","execution":{"iopub.status.busy":"2021-06-05T08:42:58.375203Z","iopub.status.idle":"2021-06-05T08:42:58.375710Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"gen_PM = gen_PM.apply(weights_init)\ngen_MP = gen_MP.apply(weights_init)\ndisc_P = disc_P.apply(weights_init)\ndisc_M = disc_M.apply(weights_init)","metadata":{"papermill":{"duration":0.638142,"end_time":"2021-06-04T20:55:19.578535","exception":false,"start_time":"2021-06-04T20:55:18.940393","status":"completed"},"tags":[],"id":"divided-cyprus","execution":{"iopub.status.busy":"2021-06-05T08:42:58.376804Z","iopub.status.idle":"2021-06-05T08:42:58.377265Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"10.3.3 Train ","metadata":{"id":"zrSU1BC-Ivr6"}},{"cell_type":"code","source":"# train()","metadata":{"papermill":{"duration":0.034529,"end_time":"2021-06-04T20:55:20.030229","exception":false,"start_time":"2021-06-04T20:55:19.9957","status":"completed"},"tags":[],"id":"waiting-hobby","execution":{"iopub.status.busy":"2021-06-05T08:42:58.378535Z","iopub.status.idle":"2021-06-05T08:42:58.378997Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### 11. Tricks And improvements","metadata":{}},{"cell_type":"markdown","source":"Feel free now to use this kernel and try some of this tips in order to imporve your model score ... \nBest of luck ... \n\nTransformer with residual blocks \n\nResidual connections between Generator and Discriminator \n\nNot using InstanceNorm at the first layer of both generator and discriminator \n\nBetter InstanceNorm layer initialization \n\nTraining a lot longer \n\nBetter Conv layer initialization \n\nResidual connection with Concatenate instead of Add \n\nData augmentations (flips, rotations, and crops) \n\nDiscriminator with label smoothing \n\nUsing external data  \n\nTrain on crops \n\nDecoder with resize-convolution \n\nDifferent number of  transformer blocks \n\nPatch discriminator \n\nLager batch size ","metadata":{}},{"cell_type":"markdown","source":"I'll stop here with this block of tips. Many techniques can be combined to obtain a high quality solution. Don't forget to put an UPvote for SBH to continue updating this notebook with other useful tips","metadata":{}},{"cell_type":"code","source":"","metadata":{"papermill":{"duration":0.034956,"end_time":"2021-06-04T20:55:20.100187","exception":false,"start_time":"2021-06-04T20:55:20.065231","status":"completed"},"tags":[],"id":"phantom-nepal"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"papermill":{"duration":0.0351,"end_time":"2021-06-04T20:55:20.16985","exception":false,"start_time":"2021-06-04T20:55:20.13475","status":"completed"},"tags":[],"id":"analyzed-accuracy"},"execution_count":null,"outputs":[]}]}