def _train(self):
for i, (images, _) in logger.enum("Train", self.train_loader):
targets_real = torch.empty(images.size(0), 1, device=self.device).uniform_(0.8, 1.0)
targets_fake = torch.empty(images.size(0), 1, device=self.device).uniform_(0.0, 0.2)
images = images.to(self.device)
self.optimizer_D.zero_grad()
logits_real = self.discriminator(images)
fake_images = self.generator(
noise(self.device, self.batch_size, self.noise_dim)).detach()
logits_fake = self.discriminator(fake_images)
discriminator_loss = DLoss(logits_real, logits_fake, targets_real, targets_fake)
discriminator_loss.backward()
self.optimizer_D.step()
self.optimizer_G.zero_grad()
fake_images = self.generator(noise(self.device, self.batch_size, self.noise_dim))
logits_fake = self.discriminator(fake_images)
generator_loss = GLoss(logits_fake, targets_real)
generator_loss.backward()
self.optimizer_G.step()
logger.store(G_Loss=generator_loss.item())
logger.store(D_Loss=discriminator_loss.item())
logger.add_global_step()
for j in range(1, 10):
img = fake_images[j].squeeze()
logger.store('generated', img)
def loop():
logger.info(a=2, b=1)
logger.add_indicator('loss_ma', IndicatorType.queue,
IndicatorOptions(queue_size=10))
for i in range(10):
logger.add_global_step(1)
logger.store(loss=100 / (i + 1), loss_ma=100 / (i + 1))
logger.write()
if (i + 1) % 2 == 0:
logger.new_line()
time.sleep(2)
def _train(self):
self.model.train()
for i, (data, target) in logger.enum("Train", self.train_loader):
data, target = data.to(self.device), target.to(self.device)
self.optimizer.zero_grad()
output = self.model(data)
loss = F.cross_entropy(output, target)
loss.backward()
self.optimizer.step()
logger.store(train_loss=loss)
logger.add_global_step()
if i % self.train_log_interval == 0:
logger.write()
def _train(self):
self.model.train()
for i, (data, target) in logger.enumerator("Train", self.train_loader):
data, target = data.to(self.device), target.to(self.device)
self.optimizer.zero_grad()
output = self.model(data)
loss = F.nll_loss(output, target)
loss.backward()
self.optimizer.step()
# Add training loss to the logger.
# The logger will queue the values and output the mean
logger.store(train_loss=loss.item())
logger.add_global_step()
# Print output to the console
if i % self.train_log_interval == 0:
# Output the indicators
logger.write()
def _train(self):
for i, (input_tensor,
target_tensor) in logger.enum("Train", self.train_loader):
encoder_hidden = self.encoder.init_hidden(self.device).double().to(
self.device)
input_tensor = input_tensor.to(self.device).unsqueeze(1)
target_tensor = target_tensor.to(self.device).double()
self.optimizer.zero_grad()
encoder_output, encoder_hidden = self.encoder(
input_tensor, encoder_hidden)
train_loss = self.loss(encoder_output, target_tensor)
train_loss.backward()
self.optimizer.step()
logger.store(loss=train_loss.item())
logger.add_global_step()
logger.write()
