BCE = reconstruction_function(recon_x, x)
# https://arxiv.org/abs/1312.6114 (Appendix B)
# 0.5 * sum(1 + log(sigma^2) - mu^2 - sigma^2)
KLD_element = mu.pow(2).add_(logvar.exp()).mul_(-1).add_(1).add_(logvar)
KLD = torch.sum(KLD_element).mul_(-0.5)
return BCE + KLD
model = VAE()
if GPU_NUMS > 0:
model.cuda()
reconstruction_function = BCELoss()
reconstruction_function.size_average = False
optimizer = Adam(model.parameters(), lr=1e-4)
dataset = ImageFolder(root='/input/face/64_crop',
transform=Compose([ToTensor()]))
train_loader = DataLoader(dataset, batch_size=BATCH_SIZE, shuffle=True)
bar = ProgressBar(EPOCH, len(train_loader), "Loss:%.3f")
model.train()
train_loss = 0
for epoch in range(EPOCH):
for ii, (image, label) in enumerate(train_loader):
mini_batch = image.shape[0]
data = Variable(image.cuda() if GPU_NUMS > 0 else image)
optimizer.zero_grad()
