def _test(self):
self.model.eval()
test_loss = 0
correct = 0
idx = 0
with torch.no_grad():
for data, target in logger.iterate("Test", self.test_loader):
data, target = data.to(self.device), target.to(self.device)
output = self.model(data)
loss = F.nll_loss(output, target, reduction='none')
indexes = [idx + i for i in range(self.test_loader.batch_size)]
values = list(loss.cpu().numpy())
logger.store('test_sample_loss', (indexes, values))
test_loss += float(np.sum(loss.cpu().numpy()))
pred = output.argmax(dim=1, keepdim=True)
values = list(pred.cpu().numpy())
logger.store('test_sample_pred', (indexes, values))
correct += pred.eq(target.view_as(pred)).sum().item()
idx += self.test_loader.batch_size
# Add test loss and accuracy to logger
logger.store(test_loss=test_loss / len(self.test_loader.dataset))
logger.store(accuracy=correct / len(self.test_loader.dataset))
def _test(self):
self.encoder.eval()
with torch.no_grad():
macro_f1s = []
test_losses = []
for input_tensor, target_tensor in logger.iterate(
"Test", self.test_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()
encoder_output, encoder_hidden = self.encoder(
input_tensor, encoder_hidden)
test_loss = self.loss(encoder_output, target_tensor)
macro_f1 = f1_score(
y_true=target_tensor.cpu().detach().numpy().ravel(),
y_pred=encoder_output.cpu().detach().to(
torch.int32).numpy().ravel(),
average='macro')
test_losses.append(test_loss)
macro_f1s.append(macro_f1)
logger.store(test_loss=np.mean(test_losses))
logger.store(accuracy=np.mean(macro_f1s))
logger.write()
def _test(self):
self.model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for data, target in logger.iterate("Test", self.test_loader):
data, target = data.to(self.device), target.to(self.device)
output = self.model(data)
test_loss += F.cross_entropy(output, target, reduction='sum').item()
pred = output.argmax(dim=1, keepdim=True)
correct += pred.eq(target.view_as(pred)).sum().item()
logger.store(test_loss=test_loss / len(self.test_loader.dataset))
logger.store(accuracy=correct / len(self.test_loader.dataset))