def _build_models(self):
gpu_flag = torch.cuda.is_available()
extractor = Extractor()
classifier = Classifier()
discriminator = Discrimimator()
if gpu_flag:
self.device = torch.device('cuda:0')
else:
self.device = torch.device('cpu')
self.extractor = extractor.to(self.device)
self.classifier = classifier.to(self.device)
self.discriminator = discriminator.to(self.device)
batch_size=Batch_size_t,
shuffle=True,
num_workers=2)
source_training_loader_e = Data.DataLoader(dataset=source_training_dataset,
batch_size=Batch_size_s,
shuffle=True,
num_workers=2)
target_loader_e = Data.DataLoader(dataset=target_dataset,
batch_size=Batch_size_t,
shuffle=True,
num_workers=2)
#Training
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
E.to(device)
D.to(device)
R.to(device)
for epoch in range(num_epochs):
print('Epoch:', epoch + 1, 'Training')
# Evaluate Step
if epoch % 3 == 0:
# 1. Source_validation
source_validation_loss, source_validation_error = evaluate(
E, R, source_validation_loader, length_source_validation)
# 2. Source_training
source_training_loss, source_training_error = evaluate(
E, R, source_training_loader_d, length_source_training)
# 3. Target
target_loss, target_error = evaluate(E, R, target_loader_d,
length_target)