{"cells":[{"metadata":{},"cell_type":"markdown","source":"**This Kernel is based on PyTorch Tutorial available here:**\nhttps://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html\n"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"from __future__ import print_function\n#%matplotlib inline\nimport argparse\nimport os\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\nimport torchvision.utils as vutils\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.animation as animation\nfrom IPython.display import HTML\nimport imgaug\nimport random\nfrom imgaug import augmenters as iaa\nfrom imgaug import parameters as iap\nfrom PIL import Image\nimport os, os.path\n\nmanualSeed = random.randint(1000, 10000)\nprint(\"Random Seed: \", manualSeed)\nrandom.seed(manualSeed)\ntorch.manual_seed(manualSeed)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Root directory for dataset\ndataroot = \"../input/all-dogs/\"\nworkers = 2\nbatch_size = 32\nimage_size = 64\nnc = 3\nnz = 128\nngf = 64\nndf = 64\nnum_epochs = 350\nlr = 0.0001\nbeta1 = 0.5\n# Number of GPUs available. Use 0 for CPU mode.\nngpu = 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Dataset Creator\nrand_aff = random.uniform(3.0, 15.0)\nrand_flip = random.uniform(0.3, 1.0)\nrand_trans = random.uniform(0.3, 0.7)\nrand_contr = random.uniform(0.2, 0.9)\nrandom_transforms = [transforms.ColorJitter(contrast=rand_contr), transforms.RandomAffine(degrees=rand_aff)]\ndataset = dset.ImageFolder(root=dataroot,\n                           transform=transforms.Compose([\n                               transforms.Resize(image_size),\n                               transforms.CenterCrop(image_size),\n                               transforms.RandomHorizontalFlip(p=rand_flip),\n                               transforms.RandomApply(random_transforms, p=rand_trans),\n                               transforms.ToTensor(),\n                               transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),\n                           ]))\n# Create the dataloader\ndataloader = torch.utils.data.DataLoader(dataset, batch_size=batch_size,\n                                         shuffle=True, num_workers=workers)\n\n# Decide which device we want to run on\ndevice = torch.device(\"cuda:0\" if (torch.cuda.is_available() and ngpu > 0) else \"cpu\")\n\n# Plot some training images\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.constant_(m.bias.data, 0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Generator\nclass Generator(nn.Module):\n    def __init__(self, ngpu):\n        super(Generator, self).__init__()\n        self.ngpu = ngpu\n        self.main = nn.Sequential(\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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Create the generator\nnetG = Generator(ngpu).to(device)\n\n# Handle multi-gpu if desired\nif (device.type == 'cuda') and (ngpu > 1):\n    netG = nn.DataParallel(netG, list(range(ngpu)))\n\n# Apply the weights_init function to randomly initialize all weights\n#  to mean=0, stdev=0.2.\nnetG.apply(weights_init)\n\n# Print the model\nprint(netG)","execution_count":null,"outputs":[]},{"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            nn.Dropout2d(0.2),\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            nn.Dropout2d(0.2),\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            nn.Dropout2d(0.2),\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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Create the Discriminator\nnetD = Discriminator(ngpu).to(device)\n\n# Handle multi-gpu if desired\nif (device.type == 'cuda') and (ngpu > 1):\n    netD = nn.DataParallel(netD, list(range(ngpu)))\n\n# Apply the weights_init function to randomly initialize all weights\n#  to mean=0, stdev=0.2.\nnetD.apply(weights_init)\n\n# Print the model\nprint(netD)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Initialize BCELoss function\ncriterion = nn.BCELoss()\n\n# Create batch of latent vectors that we will use to visualize\n#  the progression of the generator\nfixed_noise = torch.randn(64, nz, 1, 1, device=device)\n\n# Establish convention for real and fake labels during training\nreal_label = 1\nfake_label = 0\n\n# Setup Adam optimizers for both G and D\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":{"trusted":true},"cell_type":"code","source":"# Training Loop\n\n# Lists to keep track of progress\nimg_list = []\nG_losses = []\nD_losses = []\niters = 0\n\nprint(\"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        ## 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":"#Visualisation\nplt.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":{"trusted":true},"cell_type":"code","source":"# Grab a batch of real images from the dataloader\nreal_batch = next(iter(dataloader))\n\n# Plot the real images\nplt.figure(figsize=(15,15))\nplt.subplot(1,2,1)\nplt.axis(\"off\")\nplt.title(\"Real Images\")\nplt.imshow(np.transpose(vutils.make_grid(real_batch[0].to(device)[:64], padding=5, normalize=True).cpu(),(1,2,0)))\n\n# Plot the fake images from the last epoch\nplt.subplot(1,2,2)\nplt.axis(\"off\")\nplt.title(\"Fake Images\")\nplt.imshow(np.transpose(img_list[-1],(1,2,0)))\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#!pip install tqdm\nfrom tqdm import tqdm\nfrom torchvision.utils import save_image\n\nif 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'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import shutil\nshutil.make_archive('images', 'zip', '../output_images')","execution_count":null,"outputs":[]}],"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}