GAN64x64.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Sep 25 09:46:43 2020

@author: caroline
"""

from __future__ import print_function
import argparse
#%matplotlib inline
import argparse
import os
import random
import torch
import torch.nn as nn
import torch.nn.parallel
import torch.backends.cudnn as cudnn
import torch.optim as optim
import torch.utils.data
import torchvision.datasets as dset
import torchvision.transforms as transforms
import torchvision.utils as vutils
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.animation as animation
from IPython.display import HTML



def weights_init(m):
	classname = m.__class__.__name__
	if classname.find('Conv') != -1:
		nn.init.normal_(m.weight.data, 0.0, 0.02)
	elif classname.find('BatchNorm') != -1:
		nn.init.normal_(m.weight.data, 1.0, 0.02)
		nn.init.constant_(m.bias.data, 0)
        
class Generator(nn.Module):
	def __init__(self, ngpu):
		super(Generator, self).__init__()
		self.ngpu = ngpu
		self.main = nn.Sequential(
            
            # input is Z, going into a convolution
            nn.ConvTranspose2d( nz, ngf * 8, 4, 1, 0, bias=False),
            nn.BatchNorm2d(ngf * 8),
            nn.ReLU(True),
            # state size. (ngf*8) x 4 x 4
            nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 4),
            nn.ReLU(True),
            # state size. (ngf*4) x 8 x 8
            nn.ConvTranspose2d( ngf * 4, ngf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 2),
            nn.ReLU(True),
            # state size. (ngf*2) x 16 x 16
            nn.ConvTranspose2d( ngf * 2, ngf, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf),
            nn.ReLU(True),
            # state size. (ngf) x 32 x 32
            nn.ConvTranspose2d( ngf, nc, 4, 2, 1, bias=False),
            nn.Tanh()
            # state size. (nc) x 64 x 64
        )
	def forward(self, input):
		return self.main(input)
    
class  Discriminator(nn.Module):
	def __init__(self, ngpu):
		super(Discriminator, self).__init__()
		self.ngpu = ngpu
		self.main = nn.Sequential(
            # input is (nc) x 64 x 64
            nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf) x 32 x 32
            nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 2),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf*2) x 16 x 16
            nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 4),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf*4) x 8 x 8
            nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 8),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf*8) x 4 x 4
            nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),
            nn.Sigmoid()
        )
	
	def forward(self, input):
		return self.main(input)

def main(imageType, testing=False, GIF = False):
    #create generator
    netG = Generator(ngpu).to(device)
    netD = Discriminator(ngpu).to(device)
    # Handle multi-gpu if desired
    if (device.type == 'cuda') and (ngpu > 1):
        netG = nn.DataParallel(netG, list(range(ngpu)))
        netD = nn.DataParallel(netD, list(range(ngpu)))

    # Apply the weights_init function to randomly initialize all weightsto mean=0, stdev=0.2.
    netG.apply(weights_init)
    netD.apply(weights_init)
        
    if(testing):
        print(netG)
        print(netD)
        
    # Initialize BCELoss function
    criterion = nn.BCELoss()

    # Create batch of latent vectors that we will use to visualize
    #  the progression of the generator
    fixed_noise = torch.randn(64, nz, 1, 1, device=device)
    
    # Establish convention for real and fake labels during training
    real_label = 1.
    fake_label = 0.

    # Setup Adam optimizers for both G and D
    optimizerD = optim.Adam(netD.parameters(), lr=lr, betas=(beta1, 0.999))
    optimizerG = optim.Adam(netG.parameters(), lr=lr, betas=(beta1, 0.999))
    
    # Lists to keep track of progress
    img_list = []
    G_losses = []
    D_losses = []
    
    
    print("Starting Training Loop...")
    # For each epoch
    for epoch in range(num_epochs):
        iters = 0
        # For each batch in the dataloader
        for i, data in enumerate(dataloader, 0):
    
            ############################
            # (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))
            ###########################
            ## Train with all-real batch
            netD.zero_grad()
            # Format batch
            real_cpu = data[0].to(device)
            b_size = real_cpu.size(0)
            label = torch.full((b_size,), real_label, dtype=torch.float, device=device)
            # Forward pass real batch through D
            output = netD(real_cpu).view(-1)
            # Calculate loss on all-real batch
            errD_real = criterion(output, label)
            # Calculate gradients for D in backward pass
            errD_real.backward()
            D_x = output.mean().item()
    
            ## Train with all-fake batch
            # Generate batch of latent vectors
            noise = torch.randn(b_size, nz, 1, 1, device=device)
            # Generate fake image batch with G
            fake = netG(noise)
            label.fill_(fake_label)
            # Classify all fake batch with D
            output = netD(fake.detach()).view(-1)
            # Calculate D's loss on the all-fake batch
            errD_fake = criterion(output, label)
            # Calculate the gradients for this batch
            errD_fake.backward()
            D_G_z1 = output.mean().item()
            # Add the gradients from the all-real and all-fake batches
            errD = errD_real + errD_fake
            # Update D
            optimizerD.step()
    
            ############################
            # (2) Update G network: maximize log(D(G(z)))
            ###########################
            netG.zero_grad()
            label.fill_(real_label)  # fake labels are real for generator cost
            # Since we just updated D, perform another forward pass of all-fake batch through D
            output = netD(fake).view(-1)
            # Calculate G's loss based on this output
            errG = criterion(output, label)
            # Calculate gradients for G
            errG.backward()
            D_G_z2 = output.mean().item()
            # Update G
            optimizerG.step()
    
            # Output training stats
            if i % 50 == 0:
                print('[%d/%d][%d/%d]\tLoss_D: %.4f\tLoss_G: %.4f\tD(x): %.4f\tD(G(z)): %.4f / %.4f'
                      % (epoch, num_epochs, i, len(dataloader),
                         errD.item(), errG.item(), D_x, D_G_z1, D_G_z2))
    
            # Save Losses for plotting later
            G_losses.append(errG.item())
            D_losses.append(errD.item())
            
            if GIF and (iters % 20 == 0):
                with torch.no_grad():
                    fake = netG(fixed_noise).detach().cpu()
                    
                """
                fig1, ax1 = plt.subplots()
                ax1.axis("off")
                
                print(np.transpose(vutils.make_grid(fake[0], normalize=True),(1,2,0)).size())
                fig1.savefig("GeneratedImages/GAN/args/fake_e_"+str(epoch)+"_"+str(iters) +".png")
                """
                arr = np.transpose(vutils.make_grid(fake[0], normalize=True),(1,2,0))
                dpi = 96
                fig = plt.figure(frameon=False)
                fig.set_size_inches(arr.shape[1]/dpi, arr.shape[0]/dpi)
                ax = plt.Axes(fig, [0., 0., 1., 1.])
                ax.set_axis_off()
                fig.add_axes(ax)
                ax.imshow(arr)
              
                plt.savefig("GeneratedImages/GAN/"+ str(imageType)+ "/fake_e_"+str(epoch)+"_"+str(iters) +".png", dpi=dpi)
                            
            # Check how the generator is doing by saving G's output on fixed_noise
            if (iters % 500 == 0) or ((epoch == num_epochs-1) and (i == len(dataloader)-1)):
                with torch.no_grad():
                    fake = netG(fixed_noise).detach().cpu()
                img_list.append(vutils.make_grid(fake, padding=2, normalize=True))
    
            iters += 1
            
           
       
    
    
    
if __name__ == "__main__":
    
    # Set random seed for reproducibility
    #manualSeed = 999
    manualSeed = random.randint(1, 10000) # use if you want new results
    print("Random Seed: ", manualSeed)
    random.seed(manualSeed)
    torch.manual_seed(manualSeed)
    
    dataroot = "Datasets/Stone/"
    imageType = "Stone"
    workers = 2
    batch_size = 16
    image_size = 64
    nc = 3
    nz = 100
    ngf = 64
    ndf = 64
    num_epochs = 1
    lr = 0.0002
    beta1 = 0.5
    ngpu = 0
    parser = argparse.ArgumentParser()
    parser.add_argument("-i", "--imageType", type=str, help="Image type : 'Gaussian64x64', or 'Stone'")
    parser.add_argument("-e","--epochs", type=int, help="number of epochs")
    parser.add_argument("-b", "--batch_size", type=int, help="size of the batch to be consider during training")
    parser.add_argument("-g", "--ngpu", type=int, help="number of available gpus")
    args = parser.parse_args()
    print("datapath :  Datasets/", args.imageType)

    if args.imageType is not None:
        imageType = args.imageType
        dataroot = "Datasets/" + args.imageType + "/"
    if args.batch_size is not None:
        batch_size = args.batch_size
    if args.epochs is not None:
        num_epochs = args.epochs
    if args.ngpu is not None:
        ngpu = args.ngpu
    
    dataset = dset.ImageFolder(root=dataroot,
                               transform=transforms.Compose([
                                   transforms.Resize(image_size),
                                   transforms.CenterCrop(image_size),
                                   transforms.ToTensor(),
                                   transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
                               ]))
    
    dataloader = torch.utils.data.DataLoader(dataset, batch_size=batch_size,
                                             shuffle=True, num_workers=workers)
    
    device = torch.device("cuda:0" if (torch.cuda.is_available() and ngpu > 0) else "cpu")
    
    # Plot some training images
    real_batch = next(iter(dataloader))
    print(real_batch[0].type())
    plt.figure(figsize=(2, 2))
    plt.axis("off")
    plt.title("Training Images")
    plt.imshow(np.transpose(vutils.make_grid(real_batch[0].to(device)[:4], padding=2, normalize=True).cpu(),(1,2,0)))
    testing = False
    GIF = True
    main(str(imageType),testing, GIF)