@@ -1,53 +1,22 @@
-import argparse
-import os
-import numpy as np
-import math
-
-import torchvision.transforms as transforms
-from torchvision.utils import save_image
-
-from torch.utils.data import DataLoader
-from torchvision import datasets
-from torch.autograd import Variable
-
-import torch.nn as nn
-import torch.nn.functional as F
import torch
-
-os.makedirs("images", exist_ok=True)
-
-parser = argparse.ArgumentParser()
-parser.add_argument("--n_epochs", type=int, default=200, help="number of epochs of training")
-parser.add_argument("--batch_size", type=int, default=64, help="size of the batches")
-parser.add_argument("--lr", type=float, default=0.0002, help="adam: learning rate")
-parser.add_argument("--b1", type=float, default=0.5, help="adam: decay of first order momentum of gradient")
-parser.add_argument("--b2", type=float, default=0.999, help="adam: decay of first order momentum of gradient")
-parser.add_argument("--n_cpu", type=int, default=8, help="number of cpu threads to use during batch generation")
-parser.add_argument("--latent_dim", type=int, default=100, help="dimensionality of the latent space")
-parser.add_argument("--img_size", type=int, default=32, help="size of each image dimension")
-parser.add_argument("--channels", type=int, default=1, help="number of image channels")
-parser.add_argument("--sample_interval", type=int, default=400, help="interval between image sampling")
-opt = parser.parse_args()
-print(opt)
-
-cuda = True if torch.cuda.is_available() else False
+import torch.nn as nn
def weights_init_normal(m):
- classname = m.__class__.__name__
- if classname.find("Conv") != -1:
+ class_name = m.__class__.__name__
+ if class_name.find("Conv") != -1:
torch.nn.init.normal_(m.weight.data, 0.0, 0.02)
- elif classname.find("BatchNorm2d") != -1:
+ elif class_name.find("BatchNorm2d") != -1:
torch.nn.init.normal_(m.weight.data, 1.0, 0.02)
torch.nn.init.constant_(m.bias.data, 0.0)
class Generator(nn.Module):
- def __init__(self):
+ def __init__(self, img_size, latent_dim, channels):
super(Generator, self).__init__()
- self.init_size = opt.img_size // 4
- self.l1 = nn.Sequential(nn.Linear(opt.latent_dim, 128 * self.init_size ** 2))
+ self.init_size = img_size // 4
+ self.l1 = nn.Sequential(nn.Linear(latent_dim, 128 * self.init_size ** 2))
self.conv_blocks = nn.Sequential(
nn.BatchNorm2d(128),
@@ -56,14 +25,15 @@ class Generator(nn.Module):
nn.BatchNorm2d(128, 0.8),
nn.LeakyReLU(0.2, inplace=True),
nn.Upsample(scale_factor=2),
- nn.Conv2d(128, 64, 3, stride=1, padding=1),
- nn.BatchNorm2d(64, 0.8),
+ nn.Conv2d(128, 32, 3, stride=1, padding=1),
+ nn.BatchNorm2d(32, 0.8),
nn.LeakyReLU(0.2, inplace=True),
- nn.Conv2d(64, opt.channels, 3, stride=1, padding=1),
- nn.Tanh(),
+ nn.Conv2d(32, channels, 3, stride=1, padding=1),
+ nn.Tanh()
)
def forward(self, z):
+ z=z.view(z.size(0),-1)
out = self.l1(z)
out = out.view(out.shape[0], 128, self.init_size, self.init_size)
img = self.conv_blocks(out)
@@ -71,7 +41,7 @@ class Generator(nn.Module):
class Discriminator(nn.Module):
- def __init__(self):
+ def __init__(self, img_size, channels):
super(Discriminator, self).__init__()
def discriminator_block(in_filters, out_filters, bn=True):
@@ -81,15 +51,15 @@ class Discriminator(nn.Module):
return block
self.model = nn.Sequential(
- *discriminator_block(opt.channels, 16, bn=False),
+ *discriminator_block(channels, 16, bn=False),
*discriminator_block(16, 32),
*discriminator_block(32, 64),
*discriminator_block(64, 128),
)
- # The height and width of downsampled image
- ds_size = opt.img_size // 2 ** 4
- self.adv_layer = nn.Sequential(nn.Linear(128 * ds_size ** 2, 1), nn.Sigmoid())
+ # The height and width of down_sampled image
+ ds_size = img_size // 2 ** 4
+ self.adv_layer = nn.Sequential(nn.Linear(128 * ds_size ** 2, 1))
def forward(self, img):
out = self.model(img)
@@ -98,95 +68,3 @@ class Discriminator(nn.Module):
return validity
-
-# Loss function
-adversarial_loss = torch.nn.BCELoss()
-
-# Initialize generator and discriminator
-generator = Generator()
-discriminator = Discriminator()
-
-if cuda:
- generator.cuda()
- discriminator.cuda()
- adversarial_loss.cuda()
-
-# Initialize weights
-generator.apply(weights_init_normal)
-discriminator.apply(weights_init_normal)
-
-# Configure data loader
-os.makedirs("../../data/mnist", exist_ok=True)
-dataloader = torch.utils.data.DataLoader(
- datasets.MNIST(
- "../../data/mnist",
- train=True,
- download=True,
- transform=transforms.Compose(
- [transforms.Resize(opt.img_size), transforms.ToTensor(), transforms.Normalize([0.5], [0.5])]
- ),
- ),
- batch_size=opt.batch_size,
- shuffle=True,
-)
-
-# Optimizers
-optimizer_G = torch.optim.Adam(generator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
-optimizer_D = torch.optim.Adam(discriminator.parameters(), lr=opt.lr, betas=(opt.b1, opt.b2))
-
-Tensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
-
-# ----------
-# Training
-# ----------
-
-for epoch in range(opt.n_epochs):
- for i, (imgs, _) in enumerate(dataloader):
-
- # Adversarial ground truths
- valid = Variable(Tensor(imgs.shape[0], 1).fill_(1.0), requires_grad=False)
- fake = Variable(Tensor(imgs.shape[0], 1).fill_(0.0), requires_grad=False)
-
- # Configure input
- real_imgs = Variable(imgs.type(Tensor))
-
- # -----------------
- # Train Generator
- # -----------------
-
- optimizer_G.zero_grad()
-
- # Sample noise as generator input
- z = Variable(Tensor(np.random.normal(0, 1, (imgs.shape[0], opt.latent_dim))))
-
- # Generate a batch of images
- gen_imgs = generator(z)
-
- # Loss measures generator's ability to fool the discriminator
- g_loss = adversarial_loss(discriminator(gen_imgs), valid)
-
- g_loss.backward()
- optimizer_G.step()
-
- # ---------------------
- # Train Discriminator
- # ---------------------
-
- optimizer_D.zero_grad()
-
- # Measure discriminator's ability to classify real from generated samples
- real_loss = adversarial_loss(discriminator(real_imgs), valid)
- fake_loss = adversarial_loss(discriminator(gen_imgs.detach()), fake)
- d_loss = (real_loss + fake_loss) / 2
-
- d_loss.backward()
- optimizer_D.step()
-
- print(
- "[Epoch %d/%d] [Batch %d/%d] [D loss: %f] [G loss: %f]"
- % (epoch, opt.n_epochs, i, len(dataloader), d_loss.item(), g_loss.item())
- )
-
- batches_done = epoch * len(dataloader) + i
- if batches_done % opt.sample_interval == 0:
- save_image(gen_imgs.data[:25], "images/%d.png" % batches_done, nrow=5, normalize=True)