Lines Matching full:loss

17         self.loss = np.loadtxt(loss_file, dtype='float32')
19         self.nb_sequences = self.loss.shape[0]//self.sequence_length
20         self.loss = self.loss[:self.nb_sequences*self.sequence_length]
21 …erc = lfilter(np.array([.001], dtype='float32'), np.array([1., -.999], dtype='float32'), self.loss)
23         self.loss = np.reshape(self.loss, (self.nb_sequences, self.sequence_length, 1))
34         return [self.loss[index, :, :], perc]
73             for i, (loss, perc) in enumerate(tepoch):
75                 loss = loss.to(device)  variable
78                 out, states = model(loss, perc, states=states)
81                 target = loss[:,1:,:]
83 …            loss = torch.mean(-target*torch.log(out+epsilon) - (1-target)*torch.log(1-out+epsilon))  variable
85                 loss.backward()
90                 running_loss += loss.detach().cpu().item()
91                 tepoch.set_postfix(loss=f"{running_loss/(i+1):8.5f}",
97         checkpoint['loss'] = running_loss / len(dataloader)