问模型拟合时抑制数值或平滑结果

EN

def train(self):
        steps, losses, metrics = TrainingUtilities.get_training_variables(self.parameters)
        patience_counter = 0
        best_epoch_data = None
        best_epoch_validation_loss = 999
        best_epoch = 0
        exit_training = False
        try:
            for epoch in range(steps, self.epoch_count):
                epoch_metrics = TrainingUtilities.initialize_metrics(self.mode)
                if exit_training:
                    break
                for idx, phase in enumerate(['train', 'val']):
                    if phase == 'train':
                        self.model.train()
                    else:
                        self.model.eval()
                    for _, data in tqdm(enumerate(self.data_loaders[idx])):

                        self.optimizer.zero_grad()
                        inputs, labels = data

                        outputs = self.model(inputs.to(self.device))
                        # labels = azi_class.squeeze_().to(self.device)
                        loss = self.criterion(outputs.squeeze(), labels.to(self.device))

                        epoch_metrics = TrainingUtilities.get_epoch_metrics(
                            outputs, labels, loss, epoch_metrics, phase, self.mode)

                        if phase == 'train':
                            loss.backward()
                            self.optimizer.step()

                    TrainingUtilities.report_metrics(self.writer, epoch_metrics, epoch, phase, self.parameters, self.mode)
                    if phase == "val":
                        TrainingUtilities.step_scheduler(
                            self.scheduler, np.mean(epoch_metrics[0][phase]), self.parameters)
                  
                losses.append(epoch_metrics[0])
                metrics.append(epoch_metrics)
                if epoch % self.epoch_save_count == 0:
                    TrainingUtilities.save_checkpoint(self.model, losses, metrics, self.training_dir, epoch, self.mode, self.model_name, self.size)

                steps += 1

        except (KeyboardInterrupt, RuntimeError) as error:
            print(f"Error: {error}")
            TrainingUtilities.save_checkpoint(self.model, losses, metrics, self.training_dir, steps, self.mode, self.model_name, self.size)