in torchbenchmark/models/pytorch_stargan/solver.py [0:0]
def train(self, debug=''):
"""Train StarGAN within a single dataset."""
# Set data loader.
if self.dataset == 'CelebA':
data_loader = self.celeba_loader
elif self.dataset == 'RaFD':
data_loader = self.rafd_loader
# Fetch fixed inputs for debugging.
data_iter = iter(data_loader)
x_fixed, c_org = next(data_iter)
x_fixed = x_fixed.to(self.device)
c_fixed_list = self.create_labels(c_org, self.c_dim, self.dataset, self.selected_attrs)
# Learning rate cache for decaying.
g_lr = self.g_lr
d_lr = self.d_lr
# Start training from scratch or resume training.
start_iters = 0
if self.resume_iters:
start_iters = self.resume_iters
self.restore_model(self.resume_iters)
# Start training.
print('Start training...')
start_time = time.time()
for i in range(start_iters, self.num_iters):
# =================================================================================== #
# 1. Preprocess input data #
# =================================================================================== #
# Fetch real images and labels.
try:
x_real, label_org = next(data_iter)
except:
data_iter = iter(data_loader)
x_real, label_org = next(data_iter)
# Generate target domain labels randomly.
rand_idx = torch.randperm(label_org.size(0))
label_trg = label_org[rand_idx]
if self.dataset == 'CelebA':
c_org = label_org.clone()
c_trg = label_trg.clone()
elif self.dataset == 'RaFD':
c_org = self.label2onehot(label_org, self.c_dim)
c_trg = self.label2onehot(label_trg, self.c_dim)
x_real = x_real.to(self.device) # Input images.
c_org = c_org.to(self.device) # Original domain labels.
c_trg = c_trg.to(self.device) # Target domain labels.
label_org = label_org.to(self.device) # Labels for computing classification loss.
label_trg = label_trg.to(self.device) # Labels for computing classification loss.
# =================================================================================== #
# 2. Train the discriminator #
# =================================================================================== #
# Compute loss with real images.
out_src, out_cls = self.D(x_real)
d_loss_real = - torch.mean(out_src)
d_loss_cls = self.classification_loss(out_cls, label_org, self.dataset)
# Compute loss with fake images.
x_fake = self.G(x_real, c_trg)
out_src, out_cls = self.D(x_fake.detach())
d_loss_fake = torch.mean(out_src)
# Save the last value to reference.out
if i == self.num_iters - 1 and debug:
to_be_saved = d_loss_cls - d_loss_fake
torch.save(to_be_saved, debug)
# Compute loss for gradient penalty.
alpha = torch.rand(x_real.size(0), 1, 1, 1).to(self.device)
x_hat = (alpha * x_real.data + (1 - alpha) * x_fake.data).requires_grad_(True)
out_src, _ = self.D(x_hat)
d_loss_gp = self.gradient_penalty(out_src, x_hat)
# Backward and optimize.
d_loss = d_loss_real + d_loss_fake + self.lambda_cls * d_loss_cls + self.lambda_gp * d_loss_gp
self.reset_grad()
d_loss.backward()
self.d_optimizer.step()
# Logging.
loss = {}
loss['D/loss_real'] = d_loss_real.item()
loss['D/loss_fake'] = d_loss_fake.item()
loss['D/loss_cls'] = d_loss_cls.item()
loss['D/loss_gp'] = d_loss_gp.item()
# =================================================================================== #
# 3. Train the generator #
# =================================================================================== #
if (i+1) % self.n_critic == 0:
# Original-to-target domain.
x_fake = self.G(x_real, c_trg)
out_src, out_cls = self.D(x_fake)
g_loss_fake = - torch.mean(out_src)
g_loss_cls = self.classification_loss(out_cls, label_trg, self.dataset)
# Target-to-original domain.
x_reconst = self.G(x_fake, c_org)
g_loss_rec = torch.mean(torch.abs(x_real - x_reconst))
# Backward and optimize.
g_loss = g_loss_fake + self.lambda_rec * g_loss_rec + self.lambda_cls * g_loss_cls
self.reset_grad()
g_loss.backward()
self.g_optimizer.step()
# Logging.
loss['G/loss_fake'] = g_loss_fake.item()
loss['G/loss_rec'] = g_loss_rec.item()
loss['G/loss_cls'] = g_loss_cls.item()
# =================================================================================== #
# 4. Miscellaneous #
# =================================================================================== #
# Print out training information.
if (i+1) % self.log_step == 0:
et = time.time() - start_time
et = str(datetime.timedelta(seconds=et))[:-7]
log = "Elapsed [{}], Iteration [{}/{}]".format(et, i+1, self.num_iters)
for tag, value in loss.items():
log += ", {}: {:.4f}".format(tag, value)
print(log)
if self.use_tensorboard:
for tag, value in loss.items():
self.logger.scalar_summary(tag, value, i+1)
# Translate fixed images for debugging.
if (i+1) % self.sample_step == 0 and debug:
with torch.no_grad():
x_fake_list = [x_fixed]
for c_fixed in c_fixed_list:
x_fake_list.append(self.G(x_fixed, c_fixed))
x_concat = torch.cat(x_fake_list, dim=3)
sample_path = os.path.join(self.sample_dir, '{}-images.jpg'.format(i+1))
save_image(self.denorm(x_concat.data.cpu()), sample_path, nrow=1, padding=0)
print('Saved real and fake images into {}...'.format(sample_path))
# Save model checkpoints.
if (i+1) % self.model_save_step == 0:
G_path = os.path.join(self.model_save_dir, '{}-G.ckpt'.format(i+1))
D_path = os.path.join(self.model_save_dir, '{}-D.ckpt'.format(i+1))
torch.save(self.G.state_dict(), G_path)
torch.save(self.D.state_dict(), D_path)
print('Saved model checkpoints into {}...'.format(self.model_save_dir))
# Decay learning rates.
if (i+1) % self.lr_update_step == 0 and (i+1) > (self.num_iters - self.num_iters_decay):
g_lr -= (self.g_lr / float(self.num_iters_decay))
d_lr -= (self.d_lr / float(self.num_iters_decay))
self.update_lr(g_lr, d_lr)
print ('Decayed learning rates, g_lr: {}, d_lr: {}.'.format(g_lr, d_lr))