{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Generative Adversarial Networks\n# What is a GAN?\n\nGANs are a framework for teaching a DL model to capture the training data’s distribution so we can generate new data from that same distribution."},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np \nimport pandas as pd\n\nimport argparse\nimport random\nimport torch\nimport torch.nn as nn\nimport torch.nn.parallel\nimport torch.backends.cudnn as cudnn\nimport torch.optim as optim\nimport torch.utils.data\nimport torchvision.datasets as dset\nimport torchvision.transforms as transforms\nfrom torchvision.utils import save_image\nimport torchvision.utils as vutils\nimport matplotlib.pyplot as plt\nimport matplotlib.animation as animation\nfrom IPython.display import HTML\n\nmanualSeed = 999\nrandom.seed(manualSeed)\ntorch.manual_seed(manualSeed)\n\nimport os\nprint(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"\n * dataroot - the path to the root of the dataset folder. We will talk more about the dataset in the next section\n * workers - the number of worker threads for loading the data with the DataLoader\n * batch_size - the batch size used in training. The DCGAN paper uses a batch size of 128\n * image_size - the spatial size of the images used for training. This implementation defaults to 64x64. If another size is desired, the structures of D and G must be changed. See here for more details\n * nc - number of color channels in the input images. For color images this is 3\n * nz - length of latent vector\n * ngf - relates to the depth of feature maps carried through the generator\n * ndf - sets the depth of feature maps propagated through the discriminator\n * num_epochs - number of training epochs to run. Training for longer will probably lead to better results but will also take much longer\n * lr - learning rate for training. As described in the DCGAN paper, this number should be 0.0002\n * beta1 - beta1 hyperparameter for Adam optimizers. As described in paper, this number should be 0.5\n * ngpu - number of GPUs available. If this is 0, code will run in CPU mode. If this number is greater than 0 it will run on that number of GPUs\n"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"dataroot = '../input/all-dogs'\nworkers = 2\nbatch_size = 128\nimage_size = 64\nnc = 3\nnz = 100\nngf = 64\nndf = 64\nnum_epochs = 100\nlr = 0.0002\nbeta1 = 0.5\nngpu = 1\nComputeLB = False\nDogsOnly = False","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np, pandas as pd, os\nimport xml.etree.ElementTree as ET \nimport matplotlib.pyplot as plt, zipfile \nfrom PIL import Image \nfrom glob import glob\n\nROOT = '../input/generative-dog-images/'\nif not ComputeLB: ROOT = '../input/'\nIMAGES = os.listdir(ROOT + 'all-dogs/all-dogs/')\nbreeds = os.listdir(ROOT + 'annotation/Annotation/') \n\nidxIn = 0; namesIn = []\nimagesIn = np.zeros((25000,64,64,3))\n\n# CROP WITH BOUNDING BOXES TO GET DOGS ONLY\n# https://www.kaggle.com/paulorzp/show-annotations-and-breeds\nif DogsOnly:\n for breed in breeds:\n for dog in os.listdir(ROOT+'annotation/Annotation/'+breed):\n try: img = Image.open(ROOT+'all-dogs/all-dogs/'+dog+'.jpg') \n except: continue \n tree = ET.parse(ROOT+'annotation/Annotation/'+breed+'/'+dog)\n root = tree.getroot()\n objects = root.findall('object')\n for o in objects:\n bndbox = o.find('bndbox') \n xmin = int(bndbox.find('xmin').text)\n ymin = int(bndbox.find('ymin').text)\n xmax = int(bndbox.find('xmax').text)\n ymax = int(bndbox.find('ymax').text)\n w = np.min((xmax - xmin, ymax - ymin))\n img2 = img.crop((xmin, ymin, xmin+w, ymin+w))\n img2 = img2.resize((64,64), Image.ANTIALIAS)\n imagesIn[idxIn,:,:,:] = np.asarray(img2)\n #if idxIn%1000==0: print(idxIn)\n namesIn.append(breed)\n idxIn += 1\n idx = np.arange(idxIn)\n np.random.shuffle(idx)\n imagesIn = imagesIn[idx,:,:,:]\n namesIn = np.array(namesIn)[idx]\n \n# RANDOMLY CROP FULL IMAGES\nelse:\n x = np.random.choice(np.arange(20579),10000)\n for k in range(len(x)):\n img = Image.open(ROOT + 'all-dogs/all-dogs/' + IMAGES[x[k]])\n w = img.size[0]\n h = img.size[1]\n sz = np.min((w,h))\n a=0; b=0\n if w 0) else \"cpu\")\n\nreal_batch = next(iter(dataloader))\nplt.figure(figsize=(8,8))\nplt.axis(\"off\")\nplt.title(\"Training Images\")\nplt.imshow(np.transpose(vutils.make_grid(real_batch[0].to(device)[:64], padding=2, normalize=True).cpu(),(1,2,0)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def weights_init(m):\n classname = m.__class__.__name__\n if classname.find('Conv') != -1:\n nn.init.normal_(m.weight.data, 0.0, 0.02)\n elif classname.find('BatchNorm') != -1:\n nn.init.normal_(m.weight.data, 1.0, 0.02)\n nn.init.normal_(m.bias.data, 0)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Generator\n\nThe generator, G\n, is designed to map the latent space vector (z) to data-space. Since our data are images, converting z to data-space means ultimately creating a RGB image with the same size as the training images (i.e. 3x64x64). In practice, this is accomplished through a series of strided two dimensional convolutional transpose layers, each paired with a 2d batch norm layer and a relu activation. The output of the generator is fed through a tanh function to return it to the input data range of [−1,1]. It is worth noting the existence of the batch norm functions after the conv-transpose layers, as this is a critical contribution of the DCGAN paper. These layers help with the flow of gradients during training. An image of the generator from the DCGAN paper is shown below.\n\n\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"class Generator(nn.Module):\n def __init__(self, ngpu):\n super(Generator, self).__init__()\n self.ngpu = ngpu\n self.main = nn.Sequential(\n \n nn.ConvTranspose2d( nz, ngf * 8, 4, 1, 0, bias=False),\n nn.BatchNorm2d(ngf * 8),\n nn.ReLU(True),\n \n nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),\n nn.BatchNorm2d(ngf * 4),\n nn.ReLU(True),\n \n nn.ConvTranspose2d( ngf * 4, ngf * 2, 4, 2, 1, bias=False),\n nn.BatchNorm2d(ngf * 2),\n nn.ReLU(True),\n \n nn.ConvTranspose2d( ngf * 2, ngf, 4, 2, 1, bias=False),\n nn.BatchNorm2d(ngf),\n nn.ReLU(True),\n \n nn.ConvTranspose2d( ngf, nc, 4, 2, 1, bias=False),\n nn.Tanh()\n \n )\n\n def forward(self, input):\n return self.main(input)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"netG = Generator(ngpu).to(device)\nnetG.apply(weights_init)\nprint(netG)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Discriminator\n\nAs mentioned, the discriminator, D\n, is a binary classification network that takes an image as input and outputs a scalar probability that the input image is real (as opposed to fake). Here, D takes a 3x64x64 input image, processes it through a series of Conv2d, BatchNorm2d, and LeakyReLU layers, and outputs the final probability through a Sigmoid activation function. This architecture can be extended with more layers if necessary for the problem, but there is significance to the use of the strided convolution, BatchNorm, and LeakyReLUs. The DCGAN paper mentions it is a good practice to use strided convolution rather than pooling to downsample because it lets the network learn its own pooling function. Also batch norm and leaky relu functions promote healthy gradient flow which is critical for the learning process of both G and D."},{"metadata":{"trusted":true},"cell_type":"code","source":"class Discriminator(nn.Module):\n def __init__(self, ngpu):\n super(Discriminator, self).__init__()\n self.ngpu = ngpu\n self.main = nn.Sequential(\n \n nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),\n nn.LeakyReLU(0.2, inplace=True),\n \n nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),\n nn.BatchNorm2d(ndf * 2),\n nn.LeakyReLU(0.2, inplace=True),\n \n nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),\n nn.BatchNorm2d(ndf * 4),\n nn.LeakyReLU(0.2, inplace=True),\n \n nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),\n nn.BatchNorm2d(ndf * 8),\n nn.LeakyReLU(0.2, inplace=True),\n \n nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),\n nn.Sigmoid()\n )\n\n def forward(self, input):\n return self.main(input)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"netD = Discriminator(ngpu).to(device)\nnetD.apply(weights_init)\nprint(netD)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Loss Functions and Optimizers\n\nWith D\nand G\n\nsetup, we can specify how they learn through the loss functions and optimizers. We will use the Binary Cross Entropy loss (BCELoss) function which is defined in PyTorch as:\nℓ(x,y)=L={l1,…,lN}⊤,ln=−[yn⋅logxn+(1−yn)⋅log(1−xn)]\n\nNotice how this function provides the calculation of both log components in the objective function (i.e. log(D(x))\nand log(1−D(G(z)))). We can specify what part of the BCE equation to use with the y input. This is accomplished in the training loop which is coming up soon, but it is important to understand how we can choose which component we wish to calculate just by changing y\n\n(i.e. GT labels).\n\nNext, we define our real label as 1 and the fake label as 0. These labels will be used when calculating the losses of D\nand G, and this is also the convention used in the original GAN paper. Finally, we set up two separate optimizers, one for D and one for G. As specified in the DCGAN paper, both are Adam optimizers with learning rate 0.0002 and Beta1 = 0.5. For keeping track of the generator’s learning progression, we will generate a fixed batch of latent vectors that are drawn from a Gaussian distribution (i.e. fixed_noise) . In the training loop, we will periodically input this fixed_noise into G, and over the iterations we will see images form out of the noise."},{"metadata":{"trusted":true},"cell_type":"code","source":"criterion = nn.BCELoss()\n\nfixed_noise = torch.randn(64, nz, 1, 1, device=device)\n\nreal_label = 1\nfake_label = 0\n\noptimizerD = optim.Adam(netD.parameters(), lr=lr, betas=(beta1, 0.999))\noptimizerG = optim.Adam(netG.parameters(), lr=lr, betas=(beta1, 0.999))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training\n\nFinally, now that we have all of the parts of the GAN framework defined, we can train it. Be mindful that training GANs is somewhat of an art form, as incorrect hyperparameter settings lead to mode collapse with little explanation of what went wrong. Here, we will closely follow Algorithm 1 from Goodfellow’s paper, while abiding by some of the best practices shown in ganhacks. Namely, we will “construct different mini-batches for real and fake” images, and also adjust G’s objective function to maximize logD(G(z))\n\n. Training is split up into two main parts. Part 1 updates the Discriminator and Part 2 updates the Generator.\n\n* Part 1 - Train the Discriminator\n\nRecall, the goal of training the discriminator is to maximize the probability of correctly classifying a given input as real or fake. In terms of Goodfellow, we wish to “update the discriminator by ascending its stochastic gradient”. Practically, we want to maximize log(D(x))+log(1−D(G(z)))\n. Due to the separate mini-batch suggestion from ganhacks, we will calculate this in two steps. First, we will construct a batch of real samples from the training set, forward pass through D, calculate the loss (log(D(x))), then calculate the gradients in a backward pass. Secondly, we will construct a batch of fake samples with the current generator, forward pass this batch through D, calculate the loss (log(1−D(G(z)))\n\n), and accumulate the gradients with a backward pass. Now, with the gradients accumulated from both the all-real and all-fake batches, we call a step of the Discriminator’s optimizer.\n\n* Part 2 - Train the Generator\n\nAs stated in the original paper, we want to train the Generator by minimizing log(1−D(G(z)))\nin an effort to generate better fakes. As mentioned, this was shown by Goodfellow to not provide sufficient gradients, especially early in the learning process. As a fix, we instead wish to maximize log(D(G(z))). In the code we accomplish this by: classifying the Generator output from Part 1 with the Discriminator, computing G’s loss using real labels as GT, computing G’s gradients in a backward pass, and finally updating G’s parameters with an optimizer step. It may seem counter-intuitive to use the real labels as GT labels for the loss function, but this allows us to use the log(x) part of the BCELoss (rather than the log(1−x)\n\npart) which is exactly what we want.\n\nFinally, we will do some statistic reporting and at the end of each epoch we will push our fixed_noise batch through the generator to visually track the progress of G’s training. The training statistics reported are:\n\n Loss_D - discriminator loss calculated as the sum of losses for the all real and all fake batches (log(D(x))+log(D(G(z)))\n\n).\nLoss_G - generator loss calculated as log(D(G(z)))\nD(x) - the average output (across the batch) of the discriminator for the all real batch. This should start close to 1 then theoretically converge to 0.5 when G gets better. Think about why this is.\nD(G(z)) - average discriminator outputs for the all fake batch. The first number is before D is updated and the second number is after D is updated. These numbers should start near 0 and converge to 0.5 as G gets better. Think about why this is."},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"# Lists to keep track of progress\nimg_list = []\nG_losses = []\nD_losses = []\niters = 0\n\nprint(\"Starting Training Loop...\")\n# For each epoch\nfor epoch in range(num_epochs):\n # For each batch in the dataloader\n for i, data in enumerate(dataloader, 0):\n\n ############################\n # (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))\n ###########################\n ## Train with all-real batch\n netD.zero_grad()\n # Format batch\n real_cpu = data[0].to(device)\n b_size = real_cpu.size(0)\n label = torch.full((b_size,), real_label, device=device)\n # Forward pass real batch through D\n output = netD(real_cpu).view(-1)\n # Calculate loss on all-real batch\n errD_real = criterion(output, label)\n # Calculate gradients for D in backward pass\n errD_real.backward()\n D_x = output.mean().item()\n\n ## Train with all-fake batch\n # Generate batch of latent vectors\n noise = torch.randn(b_size, nz, 1, 1, device=device)\n # Generate fake image batch with G\n fake = netG(noise)\n label.fill_(fake_label)\n # Classify all fake batch with D\n output = netD(fake.detach()).view(-1)\n # Calculate D's loss on the all-fake batch\n errD_fake = criterion(output, label)\n # Calculate the gradients for this batch\n errD_fake.backward()\n D_G_z1 = output.mean().item()\n # Add the gradients from the all-real and all-fake batches\n errD = errD_real + errD_fake\n # Update D\n optimizerD.step()\n\n ############################\n # (2) Update G network: maximize log(D(G(z)))\n ###########################\n netG.zero_grad()\n label.fill_(real_label) # fake labels are real for generator cost\n # Since we just updated D, perform another forward pass of all-fake batch through D\n output = netD(fake).view(-1)\n # Calculate G's loss based on this output\n errG = criterion(output, label)\n # Calculate gradients for G\n errG.backward()\n D_G_z2 = output.mean().item()\n # Update G\n optimizerG.step()\n\n # Output training stats\n if i % 50 == 0:\n print('[%d/%d][%d/%d]\\tLoss_D: %.4f\\tLoss_G: %.4f\\tD(x): %.4f\\tD(G(z)): %.4f / %.4f'\n % (epoch, num_epochs, i, len(dataloader),\n errD.item(), errG.item(), D_x, D_G_z1, D_G_z2))\n\n # Save Losses for plotting later\n G_losses.append(errG.item())\n D_losses.append(errD.item())\n\n # Check how the generator is doing by saving G's output on fixed_noise\n if (iters % 500 == 0) or ((epoch == num_epochs-1) and (i == len(dataloader)-1)):\n with torch.no_grad():\n fake = netG(fixed_noise).detach().cpu()\n img_list.append(vutils.make_grid(fake, padding=2, normalize=True))\n\n iters += 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(10,5))\nplt.title(\"Generator and Discriminator Loss During Training\")\nplt.plot(G_losses,label=\"G\")\nplt.plot(D_losses,label=\"D\")\nplt.xlabel(\"iterations\")\nplt.ylabel(\"Loss\")\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Generated Images"},{"metadata":{"trusted":true},"cell_type":"code","source":"fig = plt.figure(figsize=(8,8))\nplt.axis(\"off\")\nims = [[plt.imshow(np.transpose(i,(1,2,0)))] for i in img_list]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if not os.path.exists('../output_images'):\n os.mkdir('../output_images')\nim_batch_size = 50\nn_images=10000\nfor i_batch in range(0, n_images, im_batch_size):\n gen_z = torch.randn(im_batch_size, 100, 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'))\n\n\nimport shutil\nshutil.make_archive('images', 'zip', '../output_images')\nprint(\"Done\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Reference\n\n* It is completly based on [pytorch documentation](https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html) as i know very little about gans \n* I will be trying to improve this kernel as i am learning more about DCGANs"},{"metadata":{},"cell_type":"markdown","source":"## UpVote if this was helpful"}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}