def _write_metrics()

in ubteacher/engine/trainer.py [0:0]

• 23 lines of code
• 13 McCabe index (conditional complexity)

    def _write_metrics(self, metrics_dict: dict):
        metrics_dict = {
            k: v.detach().cpu().item() if isinstance(v, torch.Tensor) else float(v)
            for k, v in metrics_dict.items()
        }

        # gather metrics among all workers for logging
        # This assumes we do DDP-style training, which is currently the only
        # supported method in detectron2.
        all_metrics_dict = comm.gather(metrics_dict)
        # all_hg_dict = comm.gather(hg_dict)

        if comm.is_main_process():
            if "data_time" in all_metrics_dict[0]:
                # data_time among workers can have high variance. The actual latency
                # caused by data_time is the maximum among workers.
                data_time = np.max([x.pop("data_time")
                                   for x in all_metrics_dict])
                self.storage.put_scalar("data_time", data_time)

            # average the rest metrics
            metrics_dict = {
                k: np.mean([x[k] for x in all_metrics_dict])
                for k in all_metrics_dict[0].keys()
            }

            # append the list
            loss_dict = {}
            for key in metrics_dict.keys():
                if key[:4] == "loss":
                    loss_dict[key] = metrics_dict[key]

            total_losses_reduced = sum(loss for loss in loss_dict.values())

            self.storage.put_scalar("total_loss", total_losses_reduced)
            if len(metrics_dict) > 1:
                self.storage.put_scalars(**metrics_dict)