{"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- Generative Adversarial Networks (GANs)\n- How GANs Work\n- GANs Process\n- Examples\n\n### Generative Adversarial Networks (GANs)\n\nGenerative Adversarial Networks are used to generate images that never existed before. They learn about the world (objects, animals and so forth) and create new versions of those images that never existed.\n\nThey have two components:\n\n- A **Generator** - this creates the images.\n- A **Discriminator** - this assesses the images and tells the generator if they are similar to what it has been trained on. These are based off real world examples.\n\nWhen training the network, both the generator and discriminator start from scratch and learn together.\n\n### How GANs Work\n\n\n**G** for **Generative** - this is a model that takes an input as a random noise singal and then outputs an image.\n\n![](https://camo.githubusercontent.com/a2c5a0db812c0ade199e5ccacf86c6cff4db1685/68747470733a2f2f61636975732e636f2e756b2f77702d636f6e74656e742f7468656d65732f61636975732f6d616368696e655f6c6561726e696e672f696d67732f63762f67656e657261746976652e706e67)\n\n**A** for **Adversarial** - this is the discriminator, the opponent of the generator. This is capable of learning about objects, animals or other features specified. For example: if you supply it with pictures of dogs and non-dogs, it would be able to identify the difference between the two.\n\n![](https://camo.githubusercontent.com/96c8ccb9a91b8789106c1b3dfc9d62dde9d3cbe1/68747470733a2f2f61636975732e636f2e756b2f77702d636f6e74656e742f7468656d65732f61636975732f6d616368696e655f6c6561726e696e672f696d67732f63762f6469736372696d696e61746f722d6578616d706c652e706e67)\n\nUsing this example, once the discriminator has been trained, showing the discriminator a picture that isn't a dog it will return a 0. Whereas, if you show it a dog it will return a 1.\n\n![](https://camo.githubusercontent.com/8b5978b05b5ab4cd9bfba4819a0f0e09a12c8068/68747470733a2f2f61636975732e636f2e756b2f77702d636f6e74656e742f7468656d65732f61636975732f6d616368696e655f6c6561726e696e672f696d67732f63762f6469736372696d696e61746f722d73636f7265732e706e67)\n\n**N** for **Network** - meaning the generator and discriminator are both neural networks.\n\n\n### GANs Process\n\n**Step 1** - we input a random noise signal into the generator. The generator creates some images which is used for training the discriminator. We provide the discriminator with some features/images we want it to learn and the discriminator outputs probabilities. These probabilities can be rather high as the discriminator has only just started being trained. The values are then assessed and identified. The error is calculated and these are backpropagated through the discriminator, where the weights are updated.\n\n![](https://camo.githubusercontent.com/a26a06e2437514df1bbd736480f06a86aabebef8/68747470733a2f2f61636975732e636f2e756b2f77702d636f6e74656e742f7468656d65732f61636975732f6d616368696e655f6c6561726e696e672f696d67732f63762f73746570312d6469736372696d696e61746f722e706e67)\n\nNext we train the generator. We take the batch of images that it created and put them through the discriminator again. We do not include the feature images. The generator learns by tricking the discriminator into it outputting false positives.\n\nThe discriminator will provide an output of probabilities. The values are then assessed and compared to what they should have been. The error is calculated and backpropagated through the generator and the weights are updated.\n\n![](https://camo.githubusercontent.com/07a68fab0dbea632b29d6186e298a6c05333497c/68747470733a2f2f61636975732e636f2e756b2f77702d636f6e74656e742f7468656d65732f61636975732f6d616368696e655f6c6561726e696e672f696d67732f63762f73746570312d67656e657261746f722e706e67)\n\n**Step 2** - This is the same as step 1 but the generator and discriminator are trained a little more. Through backpropagation the generator understands its mistakes and starts to make them more like the feature.\n\nThis is created through a *Deconvolutional Neural Network*.\n\n### Examples\n\n**GANs** can be used for the following:\n\n- Generating Images\n- Image Modification\n- Super Resolution\n- Assisting Artists\n- Photo-Realistic Images\n- Speech Generation\n- Face Ageing\n\n<br>\n**[It’s Training Cats and Dogs: NVIDIA Research Uses AI to Turn Cats Into Dogs, Lions and Tigers, Too](https://blogs.nvidia.com/blog/2018/04/15/nvidia-research-image-translation/)**\n<img src=\"https://blogs.nvidia.com/wp-content/uploads/2018/04/cats-dogs-nvresearch1.png\" height=\"700\" width=\"500\">\n<br>\n<img src=\"https://cdn-images-1.medium.com/max/800/1*HaExieykcOT5oI2_xKisrQ.png\" height=\"700\" width=\"500\">\n","metadata":{}},{"cell_type":"markdown","source":"# 生成式景观基本逻辑\n\n**Step 01 数据爬取**\n爬取1000+张不同类型的地块分割生成式景观设计案例\n\n**Step02 数据处理**\n将爬取的景观平面数据处理成边界+内容的两张512*512的照片形式\n\n![image.png](attachment:1d8b548f-76b8-49e7-a98e-fde4d43f5373.png)\n\n**Step 03 机器学习样本特征** 输入新边界 通过改变边界来自主生成新的景观划分\n","metadata":{},"attachments":{"1d8b548f-76b8-49e7-a98e-fde4d43f5373.png":{"image/png":"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"}}},{"cell_type":"code","source":"import os\nprint(os.listdir(\"../input\"))","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Importing the libraries**","metadata":{}},{"cell_type":"code","source":"from __future__ import print_function\nimport time\nimport torch\nimport torch.nn as nn\nimport torch.nn.parallel\nimport torch.optim as optim\nimport torch.utils.data\nimport torchvision.datasets as dset\nimport torchvision.transforms as transforms\nimport torchvision.utils as vutils\nfrom torch.autograd import Variable\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom torch import nn, optim\nimport torch.nn.functional as F\nfrom torchvision import datasets, transforms\nfrom torchvision.utils import save_image\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nfrom tqdm import tqdm_notebook as tqdm","metadata":{"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Some Landscape\n\n> The Stanford Dogs dataset contains images of 120 breeds of dogs from around the world.","metadata":{}},{"cell_type":"code","source":"#PATH = '../input/all-dogs/all-dogs/'\nPATH = '../input/landscape/2 Inter/'\n\nimages = os.listdir(PATH)\nprint(f'There are {len(os.listdir(PATH))} pictures of landscape.')\n\nfig, axes = plt.subplots(nrows=3, ncols=3, figsize=(12,10))\n\nfor indx, axis in enumerate(axes.flatten()):\n    rnd_indx = np.random.randint(0, len(os.listdir(PATH)))\n    # https://matplotlib.org/users/image_tutorial.html\n    img = plt.imread(PATH + images[rnd_indx])\n    imgplot = axis.imshow(img)\n    axis.set_title(images[rnd_indx])\n    axis.set_axis_off()\nplt.tight_layout(rect=[0, 0.03, 1, 0.95])","metadata":{"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Insights\n\nCheck this posts:\n\n>[Quick data explanation and EDA](https://www.kaggle.com/witold1/quick-data-explanation-and-eda) by @witold1\n\n> [New Insights](https://www.kaggle.com/c/generative-dog-images/discussion/97863#latest-564673)\n\n- There are pictures with more than one dog (even with  3  dogs);\n- There are pictures with the dog (-s) and person (people);\n- There are pictures with more than one person (even with  4  people);\n- There are pictures where dogs occupy less than  1/5  of the picture;\n- There are pictures with text (magazine covers, from dog shows, memes and pictures with text);\n- Even wild predators included, e.g. African wild dog or Dingo, but not wolves.\n\n**Examples**\n\n<img src=\"https://i.ibb.co/cxZ3nwd/Captura-de-pantalla-de-2019-06-29-12-31-41.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-31-41\">\n<img src=\"https://i.ibb.co/TRzg1JG/Captura-de-pantalla-de-2019-06-29-12-32-48.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-32-48\">\n<img src=\"https://i.ibb.co/LNgrSTj/Captura-de-pantalla-de-2019-06-29-12-32-28.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-32-28\">\n<img src=\"https://i.ibb.co/p1LBrz3/Captura-de-pantalla-de-2019-06-29-12-31-59.png\" alt=\"Captura-de-pantalla-de-2019-06-29-12-31-59\">\n\n","metadata":{}},{"cell_type":"markdown","source":"# Image Preprocessing\n### Check: [GAN dogs starter](https://www.kaggle.com/wendykan/gan-dogs-starter)","metadata":{}},{"cell_type":"markdown","source":"**Initial code ...**\n\n```\nbatch_size = 32\nbatchSize = 64\nimageSize = 64\n\n# 64x64 images!\ntransform = transforms.Compose([transforms.Resize(64),\n                                transforms.CenterCrop(64),\n                                transforms.ToTensor(),\n                                transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])\n\ntrain_data = datasets.ImageFolder('../input/all-dogs/', transform=transform)\n\ndataloader = torch.utils.data.DataLoader(train_data, shuffle=True,\n                                           batch_size=batch_size)\n\nimgs, label = next(iter(dataloader))\nimgs = imgs.numpy().transpose(0, 2, 3, 1)\n\n```","metadata":{}},{"cell_type":"markdown","source":"**New data Data loader and Augmentations from [RaLSGAN dogs](https://www.kaggle.com/speedwagon/ralsgan-dogs)**","metadata":{}},{"cell_type":"code","source":"batch_size = 2\nimage_size = 64\n\nrandom_transforms = [transforms.ColorJitter(), transforms.RandomRotation(degrees=20)]\ntransform = transforms.Compose([transforms.Resize(64),\n                                transforms.CenterCrop(64),\n                                transforms.RandomHorizontalFlip(p=0.5),\n                                transforms.RandomApply(random_transforms, p=0.2),\n                                transforms.ToTensor(),\n                                transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])\n\ntrain_data = datasets.ImageFolder('../input/landscape/', transform=transform)\ntrain_loader = torch.utils.data.DataLoader(train_data, shuffle=True,\n                                           batch_size=batch_size)\n                                           \nimgs, label = next(iter(train_loader))\nimgs = imgs.numpy().transpose(0, 2, 3, 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for i in range(2):\n    plt.imshow(imgs[i])\n    plt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Weights\n### Defining the weights_init function","metadata":{}},{"cell_type":"code","source":"def weights_init(m):\n    \"\"\"\n    Takes as input a neural network m that will initialize all its weights.\n    \"\"\"\n    classname = m.__class__.__name__\n    if classname.find('Conv') != -1:\n        m.weight.data.normal_(0.0, 0.02)\n    elif classname.find('BatchNorm') != -1:\n        m.weight.data.normal_(1.0, 0.02)\n        m.bias.data.fill_(0)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Generator","metadata":{}},{"cell_type":"code","source":"class G(nn.Module):\n    def __init__(self):\n        # Used to inherit the torch.nn Module\n        super(G, self).__init__()\n        # Meta Module - consists of different layers of Modules\n        self.main = nn.Sequential(\n                nn.ConvTranspose2d(100, 512, 4, stride=1, padding=0, bias=False),\n                nn.BatchNorm2d(512),\n                nn.ReLU(True),\n                nn.ConvTranspose2d(512, 256, 4, stride=2, padding=1, bias=False),\n                nn.BatchNorm2d(256),\n                nn.ReLU(True),\n                nn.ConvTranspose2d(256, 128, 4, stride=2, padding=1, bias=False),\n                nn.BatchNorm2d(128),\n                nn.ReLU(True),\n                nn.ConvTranspose2d(128, 64, 4, stride=2, padding=1, bias=False),\n                nn.BatchNorm2d(64),\n                nn.ReLU(True),\n                nn.ConvTranspose2d(64, 3, 4, stride=2, padding=1, bias=False),\n                nn.Tanh()\n                )\n        \n    def forward(self, input):\n        output = self.main(input)\n        return output\n\n# Creating the generator\nnetG = G()\nnetG.apply(weights_init)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Discriminator","metadata":{}},{"cell_type":"code","source":"# Defining the discriminator\nclass D(nn.Module):\n    def __init__(self):\n        super(D, self).__init__()\n        self.main = nn.Sequential(\n                nn.Conv2d(3, 64, 4, stride=2, padding=1, bias=False),\n                nn.LeakyReLU(negative_slope=0.2, inplace=True),\n                nn.Conv2d(64, 128, 4, stride=2, padding=1, bias=False),\n                nn.BatchNorm2d(128),\n                nn.LeakyReLU(negative_slope=0.2, inplace=True),\n                nn.Conv2d(128, 256, 4, stride=2, padding=1, bias=False),\n                nn.BatchNorm2d(256),\n                nn.LeakyReLU(negative_slope=0.2, inplace=True),\n                nn.Conv2d(256, 512, 4, stride=2, padding=1, bias=False),\n                nn.BatchNorm2d(512),\n                nn.LeakyReLU(negative_slope=0.2, inplace=True),\n                nn.Conv2d(512, 1, 4, stride=1, padding=0, bias=False),\n                nn.Sigmoid()\n                )\n        \n    def forward(self, input):\n        output = self.main(input)\n        # .view(-1) = Flattens the output into 1D instead of 2D\n        return output.view(-1)\n    \n    \n# Creating the discriminator\nnetD = D()\nnetD.apply(weights_init)\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Another setup","metadata":{}},{"cell_type":"code","source":"class Generator(nn.Module):\n    def __init__(self, nz=128, channels=3):\n        super(Generator, self).__init__()\n        \n        self.nz = nz\n        self.channels = channels\n        \n        def convlayer(n_input, n_output, k_size=4, stride=2, padding=0):\n            block = [\n                nn.ConvTranspose2d(n_input, n_output, kernel_size=k_size, stride=stride, padding=padding, bias=False),\n                nn.BatchNorm2d(n_output),\n                nn.ReLU(inplace=True),\n            ]\n            return block\n\n        self.model = nn.Sequential(\n            *convlayer(self.nz, 1024, 4, 1, 0), # Fully connected layer via convolution.\n            *convlayer(1024, 512, 4, 2, 1),\n            *convlayer(512, 256, 4, 2, 1),\n            *convlayer(256, 128, 4, 2, 1),\n            *convlayer(128, 64, 4, 2, 1),\n            nn.ConvTranspose2d(64, self.channels, 3, 1, 1),\n            nn.Tanh()\n        )\n\n    def forward(self, z):\n        z = z.view(-1, self.nz, 1, 1)\n        img = self.model(z)\n        return img\n\n    \nclass Discriminator(nn.Module):\n    def __init__(self, channels=3):\n        super(Discriminator, self).__init__()\n        \n        self.channels = channels\n\n        def convlayer(n_input, n_output, k_size=4, stride=2, padding=0, bn=False):\n            block = [nn.Conv2d(n_input, n_output, kernel_size=k_size, stride=stride, padding=padding, bias=False)]\n            if bn:\n                block.append(nn.BatchNorm2d(n_output))\n            block.append(nn.LeakyReLU(0.2, inplace=True))\n            return block\n\n        self.model = nn.Sequential(\n            *convlayer(self.channels, 32, 4, 2, 1),\n            *convlayer(32, 64, 4, 2, 1),\n            *convlayer(64, 128, 4, 2, 1, bn=True),\n            *convlayer(128, 256, 4, 2, 1, bn=True),\n            nn.Conv2d(256, 1, 4, 1, 0, bias=False),  # FC with Conv.\n        )\n\n    def forward(self, imgs):\n        logits = self.model(imgs)\n        out = torch.sigmoid(logits)\n    \n        return out.view(-1, 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training","metadata":{}},{"cell_type":"markdown","source":"**My training baseline**","metadata":{}},{"cell_type":"code","source":"!mkdir results\n!ls","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EPOCH = 15 # play with me\nLR = 0.001\ncriterion = nn.BCELoss()\noptimizerD = optim.Adam(netD.parameters(), lr=LR, betas=(0.5, 0.999))\noptimizerG = optim.Adam(netG.parameters(), lr=LR, betas=(0.5, 0.999))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This doesn't run because EPOCH = 0, change it and try ;)","metadata":{}},{"cell_type":"code","source":"for epoch in range(EPOCH):\n    for i, data in enumerate(train_loader, 0):\n        # 1st Step: Updating the weights of the neural network of the discriminator\n        netD.zero_grad()\n        \n        # Training the discriminator with a real image of the dataset\n        real,_ = data\n        input = Variable(real)\n        target = Variable(torch.ones(input.size()[0]))\n        output = netD(input)\n        errD_real = criterion(output, target)\n        \n        # Training the discriminator with a fake image generated by the generator\n        noise = Variable(torch.randn(input.size()[0], 100, 1, 1))\n        fake = netG(noise)\n        target = Variable(torch.zeros(input.size()[0]))\n        output = netD(fake.detach())\n        errD_fake = criterion(output, target)\n        \n        # Backpropagating the total error\n        errD = errD_real + errD_fake\n        errD.backward()\n        optimizerD.step()\n        \n        # 2nd Step: Updating the weights of the neural network of the generator\n        netG.zero_grad()\n        target = Variable(torch.ones(input.size()[0]))\n        output = netD(fake)\n        errG = criterion(output, target)\n        errG.backward()\n        optimizerG.step()\n        \n        # 3rd Step: Printing the losses and saving the real images and the generated images of the minibatch every 100 steps\n        print('[%d/%d][%d/%d] Loss_D: %.4f; Loss_G: %.4f' % (epoch, EPOCH, i, len(train_loader), errD.item(), errG.item()))\n        if i % 100 == 0:\n            vutils.save_image(real, '%s/real_samples.png' % \"./results\", normalize=True)\n            fake = netG(noise)\n            vutils.save_image(fake.data, '%s/fake_samples_epoch_%03d.png' % (\"./results\", epoch), normalize=True)","metadata":{"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Best public training\n- 06/29 [RaLSGAN dogs](https://www.kaggle.com/speedwagon/ralsgan-dogs) V9\n- 06/29 this kernel V5\n- some version of this kernel","metadata":{}},{"cell_type":"markdown","source":"### Parameters","metadata":{}},{"cell_type":"code","source":"#batch_size = 32\nbatch_size = 2\nLR_G = 0.001\nLR_D = 0.0005\n\nbeta1 = 0.5\nepochs = 100\n\nreal_label = 0.9\nfake_label = 0\nnz = 128\n\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Initialize models and optimizers","metadata":{}},{"cell_type":"code","source":"netG = Generator(nz).to(device)\nnetD = Discriminator().to(device)\n\ncriterion = nn.BCELoss()\n\noptimizerD = optim.Adam(netD.parameters(), lr=LR_D, betas=(beta1, 0.999))\noptimizerG = optim.Adam(netG.parameters(), lr=LR_G, betas=(beta1, 0.999))\n\nfixed_noise = torch.randn(25, nz, 1, 1, device=device)\n\nG_losses = []\nD_losses = []\nepoch_time = []","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Plot Loss per EPOCH**\n> plot_loss()","metadata":{}},{"cell_type":"code","source":"def plot_loss (G_losses, D_losses, epoch):\n    plt.figure(figsize=(10,5))\n    plt.title(\"Generator and Discriminator Loss - EPOCH \"+ str(epoch))\n    plt.plot(G_losses,label=\"G\")\n    plt.plot(D_losses,label=\"D\")\n    plt.xlabel(\"iterations\")\n    plt.ylabel(\"Loss\")\n    plt.legend()\n    plt.show()","metadata":{"_kg_hide-input":true,"_kg_hide-output":false,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Show generated images**\n> show_generated_img()","metadata":{}},{"cell_type":"code","source":"def show_generated_img(n_images=5):\n    sample = []\n    for _ in range(n_images):\n        noise = torch.randn(1, nz, 1, 1, device=device)\n        gen_image = netG(noise).to(\"cpu\").clone().detach().squeeze(0)\n        gen_image = gen_image.numpy().transpose(1, 2, 0)\n        sample.append(gen_image)\n    \n    figure, axes = plt.subplots(1, len(sample), figsize = (64,64))\n    for index, axis in enumerate(axes):\n        axis.axis('off')\n        image_array = sample[index]\n        axis.imshow(image_array)\n        \n    plt.show()\n    plt.close()","metadata":{"_kg_hide-input":true,"_kg_hide-output":false,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(train_loader)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Training Loop","metadata":{}},{"cell_type":"code","source":"for epoch in range(epochs):\n    \n    start = time.time()\n    for ii, (real_images, train_labels) in tqdm(enumerate(train_loader), total=len(train_loader)):\n        ############################\n        # (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))\n        ###########################\n        # train with real\n        netD.zero_grad()\n        real_images = real_images.to(device)\n        batch_size = real_images.size(0)\n        labels = torch.full((batch_size, 1), real_label, device=device)\n\n        output = netD(real_images)\n        errD_real = criterion(output, labels)\n        errD_real.backward()\n        D_x = output.mean().item()\n\n        # train with fake\n        noise = torch.randn(batch_size, nz, 1, 1, device=device)\n        fake = netG(noise)\n        labels.fill_(fake_label)\n        output = netD(fake.detach())\n        errD_fake = criterion(output, labels)\n        errD_fake.backward()\n        D_G_z1 = output.mean().item()\n        errD = errD_real + errD_fake\n        optimizerD.step()\n\n        ############################\n        # (2) Update G network: maximize log(D(G(z)))\n        ###########################\n        netG.zero_grad()\n        labels.fill_(real_label)  # fake labels are real for generator cost\n        output = netD(fake)\n        errG = criterion(output, labels)\n        errG.backward()\n        D_G_z2 = output.mean().item()\n        optimizerG.step()\n        \n        # Save Losses for plotting later\n        G_losses.append(errG.item())\n        D_losses.append(errD.item())\n        \n        print(len(train_loader)//2)\n        \n        if (ii+1) % (len(train_loader)//2) == 0:\n            print('[%d/%d][%d/%d] Loss_D: %.4f Loss_G: %.4f D(x): %.4f D(G(z)): %.4f / %.4f'\n                  % (epoch + 1, epochs, ii+1, len(train_loader),\n                     errD.item(), errG.item(), D_x, D_G_z1, D_G_z2))\n            \n    plot_loss (G_losses, D_losses, epoch)\n    G_losses = []\n    D_losses = []\n    if epoch % 10 == 0:\n        show_generated_img()\n\n    epoch_time.append(time.time()- start)\n    \n#             valid_image = netG(fixed_noise)","metadata":{"_kg_hide-output":false,"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print (\">> average EPOCH duration = \", np.mean(epoch_time))","metadata":{"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Generation example\n\n**WARNING,THIS CONTAINS IMAGES THAT MAY HURT THE SENSITIVITY OF SOME PEOPLE**","metadata":{}},{"cell_type":"code","source":"show_generated_img(7)","metadata":{"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if not os.path.exists('../output_images'):\n    os.mkdir('../output_images')\n    \nim_batch_size = 50\nn_images=10000\n\nfor i_batch in tqdm(range(0, n_images, im_batch_size)):\n    gen_z = torch.randn(im_batch_size, nz, 1, 1, device=device)\n    gen_images = netG(gen_z)\n    images = gen_images.to(\"cpu\").clone().detach()\n    images = images.numpy().transpose(0, 2, 3, 1)\n    for i_image in range(gen_images.size(0)):\n        save_image(gen_images[i_image, :, :, :], os.path.join('../output_images', f'image_{i_batch+i_image:05d}.png'))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig = plt.figure(figsize=(25, 16))\n# display 10 images from each class\nfor i, j in enumerate(images[:32]):\n    ax = fig.add_subplot(4, 8, i + 1, xticks=[], yticks=[])\n    plt.imshow(j)","metadata":{"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Submission","metadata":{}},{"cell_type":"code","source":"import shutil\nshutil.make_archive('images', 'zip', '../output_images')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Save models","metadata":{}},{"cell_type":"code","source":"torch.save(netG.state_dict(), 'generator.pth')\ntorch.save(netD.state_dict(), 'discriminator.pth')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# MiFID metric","metadata":{}},{"cell_type":"markdown","source":"Base code from [Demo MiFID metric for Dog image generation comp](https://www.kaggle.com/wendykan/demo-mifid-metric-for-dog-image-generation-comp)","metadata":{}},{"cell_type":"code","source":"from __future__ import absolute_import, division, print_function\nimport numpy as np\nimport os\nimport gzip, pickle\nimport tensorflow as tf\nfrom scipy import linalg\nimport pathlib\nimport urllib\nimport warnings\nfrom PIL import Image\n\nclass KernelEvalException(Exception):\n    pass\n\nmodel_params = {\n    'Inception': {\n        'name': 'Inception', \n        'imsize': 64,\n        'output_layer': 'Pretrained_Net/pool_3:0', \n        'input_layer': 'Pretrained_Net/ExpandDims:0',\n        'output_shape': 2048,\n        'cosine_distance_eps': 0.1\n        }\n}\n\ndef create_model_graph(pth):\n    \"\"\"Creates a graph from saved GraphDef file.\"\"\"\n    # Creates graph from saved graph_def.pb.\n    with tf.gfile.FastGFile( pth, 'rb') as f:\n        graph_def = tf.GraphDef()\n        graph_def.ParseFromString( f.read())\n        _ = tf.import_graph_def( graph_def, name='Pretrained_Net')\n\ndef _get_model_layer(sess, model_name):\n    # layername = 'Pretrained_Net/final_layer/Mean:0'\n    layername = model_params[model_name]['output_layer']\n    layer = sess.graph.get_tensor_by_name(layername)\n    ops = layer.graph.get_operations()\n    for op_idx, op in enumerate(ops):\n        for o in op.outputs:\n            shape = o.get_shape()\n            if shape._dims != []:\n              shape = [s.value for s in shape]\n              new_shape = []\n              for j, s in enumerate(shape):\n                if s == 1 and j == 0:\n                  new_shape.append(None)\n                else:\n                  new_shape.append(s)\n              o.__dict__['_shape_val'] = tf.TensorShape(new_shape)\n    return layer\n\ndef get_activations(images, sess, model_name, batch_size=50, verbose=False):\n    \"\"\"Calculates the activations of the pool_3 layer for all images.\n\n    Params:\n    -- images      : Numpy array of dimension (n_images, hi, wi, 3). The values\n                     must lie between 0 and 256.\n    -- sess        : current session\n    -- batch_size  : the images numpy array is split into batches with batch size\n                     batch_size. A reasonable batch size depends on the disposable hardware.\n    -- verbose    : If set to True and parameter out_step is given, the number of calculated\n                     batches is reported.\n    Returns:\n    -- A numpy array of dimension (num images, 2048) that contains the\n       activations of the given tensor when feeding inception with the query tensor.\n    \"\"\"\n    inception_layer = _get_model_layer(sess, model_name)\n    n_images = images.shape[0]\n    if batch_size > n_images:\n        print(\"warning: batch size is bigger than the data size. setting batch size to data size\")\n        batch_size = n_images\n    n_batches = n_images//batch_size + 1\n    pred_arr = np.empty((n_images,model_params[model_name]['output_shape']))\n    for i in tqdm(range(n_batches)):\n        if verbose:\n            print(\"\\rPropagating batch %d/%d\" % (i+1, n_batches), end=\"\", flush=True)\n        start = i*batch_size\n        if start+batch_size < n_images:\n            end = start+batch_size\n        else:\n            end = n_images\n                    \n        batch = images[start:end]\n        pred = sess.run(inception_layer, {model_params[model_name]['input_layer']: batch})\n        pred_arr[start:end] = pred.reshape(-1,model_params[model_name]['output_shape'])\n    if verbose:\n        print(\" done\")\n    return pred_arr\n\n\n# def calculate_memorization_distance(features1, features2):\n#     neigh = NearestNeighbors(n_neighbors=1, algorithm='kd_tree', metric='euclidean')\n#     neigh.fit(features2) \n#     d, _ = neigh.kneighbors(features1, return_distance=True)\n#     print('d.shape=',d.shape)\n#     return np.mean(d)\n\ndef normalize_rows(x: np.ndarray):\n    \"\"\"\n    function that normalizes each row of the matrix x to have unit length.\n\n    Args:\n     ``x``: A numpy matrix of shape (n, m)\n\n    Returns:\n     ``x``: The normalized (by row) numpy matrix.\n    \"\"\"\n    return np.nan_to_num(x/np.linalg.norm(x, ord=2, axis=1, keepdims=True))\n\n\ndef cosine_distance(features1, features2):\n    # print('rows of zeros in features1 = ',sum(np.sum(features1, axis=1) == 0))\n    # print('rows of zeros in features2 = ',sum(np.sum(features2, axis=1) == 0))\n    features1_nozero = features1[np.sum(features1, axis=1) != 0]\n    features2_nozero = features2[np.sum(features2, axis=1) != 0]\n    norm_f1 = normalize_rows(features1_nozero)\n    norm_f2 = normalize_rows(features2_nozero)\n\n    d = 1.0-np.abs(np.matmul(norm_f1, norm_f2.T))\n    print('d.shape=',d.shape)\n    print('np.min(d, axis=1).shape=',np.min(d, axis=1).shape)\n    mean_min_d = np.mean(np.min(d, axis=1))\n    print('distance=',mean_min_d)\n    return mean_min_d\n\n\ndef distance_thresholding(d, eps):\n    if d < eps:\n        return d\n    else:\n        return 1\n\ndef calculate_frechet_distance(mu1, sigma1, mu2, sigma2, eps=1e-6):\n    \"\"\"Numpy implementation of the Frechet Distance.\n    The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1)\n    and X_2 ~ N(mu_2, C_2) is\n            d^2 = ||mu_1 - mu_2||^2 + Tr(C_1 + C_2 - 2*sqrt(C_1*C_2)).\n            \n    Stable version by Dougal J. Sutherland.\n\n    Params:\n    -- mu1 : Numpy array containing the activations of the pool_3 layer of the\n             inception net ( like returned by the function 'get_predictions')\n             for generated samples.\n    -- mu2   : The sample mean over activations of the pool_3 layer, precalcualted\n               on an representive data set.\n    -- sigma1: The covariance matrix over activations of the pool_3 layer for\n               generated samples.\n    -- sigma2: The covariance matrix over activations of the pool_3 layer,\n               precalcualted on an representive data set.\n\n    Returns:\n    --   : The Frechet Distance.\n    \"\"\"\n\n    mu1 = np.atleast_1d(mu1)\n    mu2 = np.atleast_1d(mu2)\n\n    sigma1 = np.atleast_2d(sigma1)\n    sigma2 = np.atleast_2d(sigma2)\n\n    assert mu1.shape == mu2.shape, \"Training and test mean vectors have different lengths\"\n    assert sigma1.shape == sigma2.shape, \"Training and test covariances have different dimensions\"\n\n    diff = mu1 - mu2\n\n    # product might be almost singular\n    covmean, _ = linalg.sqrtm(sigma1.dot(sigma2), disp=False)\n    if not np.isfinite(covmean).all():\n        msg = \"fid calculation produces singular product; adding %s to diagonal of cov estimates\" % eps\n        warnings.warn(msg)\n        offset = np.eye(sigma1.shape[0]) * eps\n        # covmean = linalg.sqrtm((sigma1 + offset).dot(sigma2 + offset))\n        covmean = linalg.sqrtm((sigma1 + offset).dot(sigma2 + offset))\n    \n    # numerical error might give slight imaginary component\n    if np.iscomplexobj(covmean):\n        if not np.allclose(np.diagonal(covmean).imag, 0, atol=1e-3):\n            m = np.max(np.abs(covmean.imag))\n            raise ValueError(\"Imaginary component {}\".format(m))\n        covmean = covmean.real\n\n    # covmean = tf.linalg.sqrtm(tf.linalg.matmul(sigma1,sigma2))\n\n    print('covmean.shape=',covmean.shape)\n    # tr_covmean = tf.linalg.trace(covmean)\n\n    tr_covmean = np.trace(covmean)\n    return diff.dot(diff) + np.trace(sigma1) + np.trace(sigma2) - 2 * tr_covmean\n    # return diff.dot(diff) + tf.linalg.trace(sigma1) + tf.linalg.trace(sigma2) - 2 * tr_covmean\n#-------------------------------------------------------------------------------\n\n\ndef calculate_activation_statistics(images, sess, model_name, batch_size=50, verbose=False):\n    \"\"\"Calculation of the statistics used by the FID.\n    Params:\n    -- images      : Numpy array of dimension (n_images, hi, wi, 3). The values\n                     must lie between 0 and 255.\n    -- sess        : current session\n    -- batch_size  : the images numpy array is split into batches with batch size\n                     batch_size. A reasonable batch size depends on the available hardware.\n    -- verbose     : If set to True and parameter out_step is given, the number of calculated\n                     batches is reported.\n    Returns:\n    -- mu    : The mean over samples of the activations of the pool_3 layer of\n               the incption model.\n    -- sigma : The covariance matrix of the activations of the pool_3 layer of\n               the incption model.\n    \"\"\"\n    act = get_activations(images, sess, model_name, batch_size, verbose)\n    mu = np.mean(act, axis=0)\n    sigma = np.cov(act, rowvar=False)\n    return mu, sigma, act\n    \ndef _handle_path_memorization(path, sess, model_name, is_checksize, is_check_png):\n    path = pathlib.Path(path)\n    files = list(path.glob('*.jpg')) + list(path.glob('*.png'))\n    imsize = model_params[model_name]['imsize']\n\n    # In production we don't resize input images. This is just for demo purpose. \n    x = np.array([np.array(img_read_checks(fn, imsize, is_checksize, imsize, is_check_png)) for fn in files])\n    m, s, features = calculate_activation_statistics(x, sess, model_name)\n    del x #clean up memory\n    return m, s, features\n\n# check for image size\ndef img_read_checks(filename, resize_to, is_checksize=False, check_imsize = 64, is_check_png = False):\n    im = Image.open(str(filename))\n    if is_checksize and im.size != (check_imsize,check_imsize):\n        raise KernelEvalException('The images are not of size '+str(check_imsize))\n    \n    if is_check_png and im.format != 'PNG':\n        raise KernelEvalException('Only PNG images should be submitted.')\n\n    if resize_to is None:\n        return im\n    else:\n        return im.resize((resize_to,resize_to),Image.ANTIALIAS)\n\ndef calculate_kid_given_paths(paths, model_name, model_path, feature_path=None):\n    ''' Calculates the KID of two paths. '''\n    tf.reset_default_graph()\n    create_model_graph(str(model_path))\n    with tf.Session() as sess:\n        sess.run(tf.global_variables_initializer())\n        m1, s1, features1 = _handle_path_memorization(paths[0], sess, model_name, is_checksize = True, is_check_png = True)\n        if feature_path is None:\n            m2, s2, features2 = _handle_path_memorization(paths[1], sess, model_name, is_checksize = False, is_check_png = False)\n        else:\n            with np.load(feature_path) as f:\n                m2, s2, features2 = f['m'], f['s'], f['features']\n\n        print('m1,m2 shape=',(m1.shape,m2.shape),'s1,s2=',(s1.shape,s2.shape))\n        print('starting calculating FID')\n        fid_value = calculate_frechet_distance(m1, s1, m2, s2)\n        print('done with FID, starting distance calculation')\n        distance = cosine_distance(features1, features2)        \n        return fid_value, distance","metadata":{"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls ../output_images","metadata":{"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**I have to fix this :(**","metadata":{}},{"cell_type":"code","source":"user_images_unzipped_path = '../output_images'\nimages_path = [user_images_unzipped_path,'../all-dogs/all-dogs/']\n\nmodel_path = '../input/dog-face-generation-competition-kid-metric-input/classify_image_graph_def.pb'\n\nfid_epsilon = 10e-15\n\nfid_value_public, distance_public = calculate_kid_given_paths(images_path, 'Inception', model_path)\ndistance_public = distance_thresholding(distance_public, model_params['Inception']['cosine_distance_eps'])\nprint(\"FID_public: \", fid_value_public, \"distance_public: \", distance_public, \"multiplied_public: \", fid_value_public /(distance_public + fid_epsilon))","metadata":{"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]}]}