return self.coder.forward(network)
NetD = Discriminator()
NetG = Generator()
optimizerD = torch.optim.Adam(NetD.parameters(),
lr=LEARNING_RATE,
betas=(0.5, 0.999))
optimizerG = torch.optim.Adam(NetG.parameters(),
lr=LEARNING_RATE,
betas=(0.5, 0.999))
dataset = epfd.Cifar10DataSetForPytorch(
root=DATA_PATH,
transform=tv.transforms.Compose([
# tv.transforms.Resize(CONFIG["IMAGE_SIZE"]),
tv.transforms.ToTensor(),
tv.transforms.Normalize([0.5] * 3, [0.5] * 3)
]))
train_loader = torch.utils.data.DataLoader(dataset,
batch_size=BATCH_SIZE,
shuffle=True)
fix_noise = torch.FloatTensor(100, NOISE_DIM).normal_(0, 1)
fix_noise_var = torch.autograd.Variable(fix_noise)
if torch.cuda.is_available() > 0:
NetG = NetG.cuda()
NetD = NetD.cuda()
fix_noise_var = fix_noise_var.cuda()
return x
trans = tv.transforms.Compose([tv.transforms.ToTensor()])
NetG = Generator()
NetD = Discriminator()
criterion = torch.nn.BCELoss()
fix_noise = torch.autograd.Variable(torch.FloatTensor(BATCH_SIZE, NOISE_DIM, 1, 1).normal_(0, 1))
if torch.cuda.is_available():
NetG = NetG.cuda()
NetD = NetD.cuda()
fix_noise = fix_noise.cuda()
criterion.cuda()
dataset = epfd.Cifar10DataSetForPytorch(train=True, transform=trans)
dataloader=torch.utils.data.DataLoader(dataset,BATCH_SIZE,shuffle = True)
optimizerD = torch.optim.Adam(NetD.parameters(), lr=LEARNING_RATE, betas=(0.5, 0.999))
optimizerG = torch.optim.Adam(NetG.parameters(), lr=LEARNING_RATE, betas=(0.5, 0.999))
bar = eup.ProgressBar(EPOCH, len(dataloader), "D Loss:%.3f;G Loss:%.3f")
for epoch in range(1, EPOCH + 1):
if epoch % 30 == 0:
optimizerD.param_groups[0]['lr'] /= 10
optimizerG.param_groups[0]['lr'] /= 10
for ii, data in enumerate(dataloader,0):
input,_=data
input = torch.autograd.Variable(input)
label = torch.ones(input.size(0))
return output
NetD = Discriminator()
NetG = Generator()
MSE_LOSS = torch.nn.MSELoss()
optimizerD = torch.optim.Adam(NetD.parameters(),
lr=LEARNING_RATE,
betas=(0.5, 0.999))
optimizerG = torch.optim.Adam(NetG.parameters(),
lr=LEARNING_RATE,
betas=(0.5, 0.999))
dataset = epfd.Cifar10DataSetForPytorch(root=DATA_PATH,
transform=tv.transforms.Compose([
tv.transforms.ToTensor(),
]))
train_loader = torch.utils.data.DataLoader(dataset,
batch_size=BATCH_SIZE,
shuffle=True)
fix_noise = torch.randn(100, NOISE_DIM)
fix_noise_var = torch.autograd.Variable(fix_noise)
if torch.cuda.is_available() > 0:
NetG = NetG.cuda()
NetD = NetD.cuda()
MSE_LOSS = MSE_LOSS.cuda()
fix_noise_var = fix_noise_var.cuda()
bar = eup.ProgressBar(EPOCH, len(train_loader), "D Loss:%.3f;G Loss:%.3f")
return x
def one_hot(target):
y = torch.zeros(target.size()[0], 10)
for i in range(target.size()[0]):
y[i, target[i]] = 1
return y
trans = tv.transforms.Compose([tv.transforms.ToTensor()])
dataset = epfd.Cifar10DataSetForPytorch(root=DATA_PATH,
train=True,
transform=trans)
dataLoader = torch.utils.data.DataLoader(dataset, BATCH_SIZE, shuffle=True)
NetG = Generator()
NetD = Discriminator()
optimizerD = torch.optim.Adam(NetD.parameters(),
lr=LEARNING_RATE,
betas=(0.5, 0.999))
optimizerG = torch.optim.Adam(NetG.parameters(),
lr=LEARNING_RATE,
betas=(0.5, 0.999))
criterion = torch.nn.BCELoss()
predict_noise = torch.randn(100, NOISE_DIM)
temp_z_ = torch.randn(10, 100)