python dcgan示例

from __future__ import print_function
#%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

dataroot = "./TrainData/image/mini"
batch_size = 256
image_size = 64

# Number of training epochs
num_epochs = 30

# Learning rate for optimizers
lr = 0.0002

# Beta1 hyperparam for Adam optimizers
beta1 = 0.5


# Generator Code

class Generator(nn.Module):
    def __init__(self):
        super(Generator, self).__init__()
        self.main = nn.Sequential(
            nn.ConvTranspose2d(100, 512, 4, 1, 0, bias=False),
            nn.BatchNorm2d(512),
            nn.ReLU(True),
            nn.ConvTranspose2d(512, 256, 4, 2, 1, bias=False),
            nn.BatchNorm2d(256),
            nn.ReLU(True),
            nn.ConvTranspose2d(256, 128, 4, 2, 1, bias=False),
            nn.BatchNorm2d(128),
            nn.ReLU(True),
            nn.ConvTranspose2d(128, 64, 4, 2, 1, bias=False),
            nn.BatchNorm2d(64),
            nn.ReLU(True),
            nn.ConvTranspose2d(64, 3, 4, 2, 1, bias=False),
            nn.Tanh()
        )

        for m in self.main.modules():
            if isinstance(m, nn.ConvTranspose2d):
                nn.init.normal_(m.weight.data, 0.0, 0.02)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.normal_(m.weight.data, 1.0, 0.02)
                nn.init.constant_(m.bias.data, 0)

    def forward(self, input):
        return self.main(input)


class Discriminator(nn.Module):
    def __init__(self):
        super(Discriminator, self).__init__()
        self.main = nn.Sequential(
            nn.Conv2d(3, 64, 4, 2, 1, bias=False),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(64, 128, 4, 2, 1, bias=False),
            nn.BatchNorm2d(128),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(128, 256, 4, 2, 1, bias=False),
            nn.BatchNorm2d(256),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(256, 512, 4, 2, 1, bias=False),
            nn.BatchNorm2d(512),
            nn.LeakyReLU(0.2, inplace=True),
            nn.Conv2d(512, 1, 4, 1, 0, bias=False),
            nn.Sigmoid()
        )

        for m in self.main.modules():
            if isinstance(m, nn.ConvTranspose2d):
                nn.init.normal_(m.weight.data, 0.0, 0.02)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.normal_(m.weight.data, 1.0, 0.02)
                nn.init.constant_(m.bias.data, 0)

    def forward(self, input):
        return self.main(input)


if __name__ == "__main__":
    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)
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    netG = Generator().to(device)
    # Create the Discriminator
    netD = Discriminator().to(device)

    # 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(batch_size, 100, 1, 1, device=device)

    # 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))

    # Training Loop

    # Lists to keep track of progress
    img_list = []
    G_losses = []
    D_losses = []
    iters = 0

    print("Starting Training Loop...")
    # For each epoch
    for epoch in range(num_epochs):
        # For each batch in the dataloader
        i = 0
        for data, label in dataloader:
            ############################
            # (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))
            ###########################
            ## Train with all-real batch
            netD.zero_grad()
            data = data.to(device)
            # Forward pass real batch through D
            output = netD(data).view(-1)
            # Calculate loss on all-real batch
            errD_real = criterion(output, torch.ones((len(output),), dtype=torch.float, device=device))
            # 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(batch_size, 100, 1, 1, device=device)
            # Generate fake image batch with G
            fake = netG(noise)
            # 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, torch.zeros((len(output),), dtype=torch.float, device=device))
            # 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()
            # 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, torch.ones((len(output),), dtype=torch.float, device=device))
            # 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))
            i += 1

            # Save Losses for plotting later
            G_losses.append(errG.item())
            D_losses.append(errD.item())

            # 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

    plt.figure(figsize=(10, 5))
    plt.title("Generator and Discriminator Loss During Training")
    plt.plot(G_losses, label="G")
    plt.plot(D_losses, label="D")
    plt.xlabel("iterations")
    plt.ylabel("Loss")
    plt.legend()

    # Grab a batch of real images from the dataloader
    real_batch = next(iter(dataloader))

    # Plot the fake images from the last epoch
    plt.subplot(1, 2, 2)
    plt.axis("off")
    plt.title("Fake Images")
    plt.imshow(np.transpose(img_list[-1], (1, 2, 0)))
    plt.show()