anime_dcgan.py

# latent = torch.randn(128, latent_size, 1, 1, device='cuda')
# trained = torch.load('random\G.pth')
# generator.load_state_dict(trained)
# generator.eval()
# result = generator(latent)

# save_image(result[1].squeeze(), 'random/image.png')


# `def show_images(images, nmax=64):
#     fig, ax = plt.subplots(figsize=(8, 8))
#     ax.set_xticks([]); ax.set_yticks([])
#     ax.imshow(make_grid(denorm(images.detach()[:nmax]), nrow=8).permute(1, 2, 0))

# def show_batch(dl, nmax=64):
#     for images, _ in dl:
#         show_images(images, nmax)
#         break`
import opendatasets as od

dataset_url = 'https://www.kaggle.com/splcher/animefacedataset'
od.download(dataset_url)

import torch
import torch.nn as nn
from torch.utils.data import DataLoader
from torchvision.datasets import ImageFolder
from torchvision.utils import make_grid
import torchvision.transforms as T
import torch.nn.functional as F
from torchvision.utils import save_image

import matplotlib.pyplot as plt
import os

DATA_DIR = 'animefacedataset/'

image_size = 64
batch_size = 128
latent_size = 128
stats = (0.5, 0.5, 0.5), (0.5, 0.5, 0.5)
device = 'cuda'

train_ds = ImageFolder(DATA_DIR, transform=T.Compose([T.Resize(image_size), T.CenterCrop(image_size), T.ToTensor(), T.Normalize(*stats)]))
train_dl = DataLoader(train_ds, batch_size, shuffle = True, num_workers = 0, pin_memory = True)

def denorm(img_tensors):
    return img_tensors * stats[1][0] + stats[0][0]

discriminator = nn.Sequential(
    # input: 3 x 128 x 128
    nn.Conv2d(3, 64, kernel_size=4, stride=2, padding=1, bias=False),
    nn.BatchNorm2d(64),
    nn.LeakyReLU(0.2, inplace=True),
    # output: 128 x 64 x 64

    nn.Conv2d(64, 128, kernel_size=4, stride=2, padding=1, bias=False),
    nn.BatchNorm2d(256),
    nn.LeakyReLU(0.2, inplace=True),
    # out: 256 x 32 x 32

    nn.Conv2d(128, 256, kernel_size=4, stride=2, padding=1, bias=False),
    nn.BatchNorm2d(512),
    nn.LeakyReLU(0.2, inplace=True),
    # out: 512 x 16 x 16

    nn.Conv2d(256, 512, kernel_size=4, stride=2, padding=1, bias=False),
    nn.BatchNorm2d(1024),
    nn.LeakyReLU(0.2, inplace=True),
    # out: 2048 x 4 x 4

    nn.Conv2d(512, 1, kernel_size=4, stride=1, padding=0, bias=False),
    # out: 1 x 1 x 1

    nn.Flatten(),
    nn.Sigmoid()
).to(device)

generator = nn.Sequential(
    # in: latent_size x 1 x 1

    nn.ConvTranspose2d(latent_size, 512, kernel_size=4, stride=1, padding=0, bias=False),
    nn.BatchNorm2d(512),
    nn.ReLU(True),
    # out: 512 x 4 x 4

    nn.ConvTranspose2d(512, 256, kernel_size=4, stride=2, padding=1, bias=False),
    nn.BatchNorm2d(256),
    nn.ReLU(True),
    # out: 256 x 8 x 8

    nn.ConvTranspose2d(256, 128, kernel_size=4, stride=2, padding=1, bias=False),
    nn.BatchNorm2d(128),
    nn.ReLU(True),
    # out: 128 x 16 x 16

    nn.ConvTranspose2d(128, 64, kernel_size=4, stride=2, padding=1, bias=False),
    nn.BatchNorm2d(64),
    nn.ReLU(True),
    # out: 64 x 32 x 32

    nn.ConvTranspose2d(64, 3, kernel_size=4, stride=2, padding=1, bias=False),
    nn.Tanh()
    # out: 3 x 64 x 64
).to(device)


def train_discriminator(real_images, opt_d):
    # Clear discriminator gradients
    opt_d.zero_grad()

    # Pass real images through discriminator
    real_preds = discriminator(real_images)
    real_targets = torch.ones(real_images.size(0), 1, device=device)
    real_loss = F.binary_cross_entropy(real_preds, real_targets)
    real_score = torch.mean(real_preds).item()
    
    # Generate fake images
    latent = torch.randn(batch_size, latent_size, 1, 1, device=device)
    fake_images = generator(latent)

    # Pass fake images through discriminator
    fake_targets = torch.zeros(fake_images.size(0), 1, device=device)
    fake_preds = discriminator(fake_images)
    fake_loss = F.binary_cross_entropy(fake_preds, fake_targets)
    fake_score = torch.mean(fake_preds).item()

    # Update discriminator weights
    loss = real_loss + fake_loss
    loss.backward()
    opt_d.step()
    return loss.item(), real_score, fake_score


def train_generator(opt_g):
    # Clear generator gradients
    opt_g.zero_grad()
    
    # Generate fake images
    latent = torch.randn(batch_size, latent_size, 1, 1, device=device)
    fake_images = generator(latent)
    
    # Try to fool the discriminator
    preds = discriminator(fake_images)
    targets = torch.ones(batch_size, 1, device=device)
    loss = F.binary_cross_entropy(preds, targets)
    
    # Update generator weights
    loss.backward()
    opt_g.step()
    
    return loss.item()

sample_dir = 'saved_images/'

def save_samples(index, latent_tensors, show=True):
    fake_images = generator(latent_tensors)
    fake_fname = 'generated-images-{0:0=4d}.png'.format(index)
    save_image(denorm(fake_images), os.path.join(sample_dir, fake_fname), nrow=8)
    print('Saving', fake_fname)
    if show:
        fig, ax = plt.subplots(figsize=(8, 8))
        ax.set_xticks([]); ax.set_yticks([])
        ax.imshow(make_grid(fake_images.cpu().detach(), nrow=8).permute(1, 2, 0))

fixed_latent = torch.randn(image_size, latent_size, 1, 1, device=device)

def fit(epochs, lr, start_idx=1):
    torch.cuda.empty_cache()
    
    # Losses & scores
    losses_g = []
    losses_d = []
    real_scores = []
    fake_scores = []
    
    # Create optimizers
    opt_d = torch.optim.Adam(discriminator.parameters(), lr=lr, betas=(0.5, 0.999))
    opt_g = torch.optim.Adam(generator.parameters(), lr=lr, betas=(0.5, 0.999))
    
    for epoch in range(epochs):
        for real_images, _ in train_dl:
            # Train discriminator
            real_images = real_images.to(device)
            loss_d, real_score, fake_score = train_discriminator(real_images, opt_d)
            # Train generator
            loss_g = train_generator(opt_g)
            
        # Record losses & scores
        losses_g.append(loss_g)
        losses_d.append(loss_d)
        real_scores.append(real_score)
        fake_scores.append(fake_score)
        
        # Log losses & scores (last batch)
        print("Epoch [{}/{}], loss_g: {:.4f}, loss_d: {:.4f}, real_score: {:.4f}, fake_score: {:.4f}".format(
            epoch+1, epochs, loss_g, loss_d, real_score, fake_score))
    
        # Save generated images
        save_samples(epoch+start_idx, fixed_latent, show=False)
    
    return losses_g, losses_d, real_scores, fake_scores

lr = 2e-4
epochs = 25

history = fit(epochs, lr)

torch.save(generator.state_dict(), 'G2.pth')
torch.save(discriminator.state_dict(), 'D2.pth')