VIPSeg Panoptic Segmentation Eval Error about dvis_plus HOT 2 CLOSED

  def process(self, inputs, outputs):
      """
      save panoptic segmentation result as an image
      """
      assert len(inputs) == 1, "More than one inputs are loaded for inference!"
      color_generator = IdGenerator(self._metadata.categories)

      # visualization of only panoptic segmentation results like this
      if 'segments_infos' not in outputs:
          mask_pred = torch.stack(outputs['pred_masks']).float()
          labels = torch.asarray(outputs['pred_labels'])
          scores = torch.asarray(outputs['pred_scores'])
          # filter out the background prediction
          keep = labels.ne(124) & (scores > 0.8)
          cur_scores = scores[keep]
          cur_classes = labels[keep]
          cur_masks = mask_pred[keep]
          # interpolation to original image size
          cur_masks = F.interpolate(
              cur_masks, size=(736, 1280), mode="bilinear", align_corners=False
          )
          cur_masks = cur_masks[:, :, :720, :1280].sigmoid()
          cur_masks = F.interpolate(
              cur_masks, size=(720, 1280), mode="bilinear", align_corners=False
          )
          cur_prob_masks = cur_scores.view(-1, 1, 1, 1).to(cur_masks.device) * cur_masks

          # initial panoptic_seg and segments infos
          h, w = cur_masks.shape[-2:]
          panoptic_seg = torch.zeros((cur_masks.size(1), h, w), dtype=torch.int32, device=cur_masks.device)
          segments_infos = []
          out_ids = []
          current_segment_id = 0

          if cur_masks.shape[0] == 0:
              # We didn't detect any mask
              outputs = {
                  "image_size": (720, 1280),
                  "pred_masks": panoptic_seg.cpu(),
                  "segments_infos": segments_infos,
                  "pred_ids": out_ids,
                  "task": "vps",
              }
          else:
              # take argmax
              cur_mask_ids = cur_prob_masks.argmax(0)  # (t, h, w)
              stuff_memory_list = {}
              for k in range(cur_classes.shape[0]):
                  pred_class = cur_classes[k].item()
                  isthing = pred_class < 58
                  # filter out the unstable segmentation results
                  mask_area = (cur_mask_ids == k).sum().item()
                  original_area = (cur_masks[k] >= 0.5).sum().item()
                  mask = (cur_mask_ids == k) & (cur_masks[k] >= 0.5)
                  if mask_area > 0 and original_area > 0 and mask.sum().item() > 0:
                      if mask_area / original_area < 0.01:  # 0.8:
                          continue
                      # merge stuff regions
                      if not isthing:
                          if int(pred_class) in stuff_memory_list.keys():
                              panoptic_seg[mask] = stuff_memory_list[int(pred_class)]
                              continue
                          else:
                              stuff_memory_list[int(pred_class)] = current_segment_id + 1
                      current_segment_id += 1
                      panoptic_seg[mask] = current_segment_id

                      segments_infos.append(
                          {
                              "id": current_segment_id,
                              "isthing": bool(isthing),
                              "category_id": int(pred_class),
                          }
                      )

              outputs = {
                  "image_size": (720, 1280),
                  "pred_masks": panoptic_seg.cpu(),
                  "segments_infos": segments_infos,
                  "pred_ids": out_ids,
                  "task": "vps",
              }

      video_id = inputs[0]["video_id"]
      image_names = [inputs[0]['file_names'][idx] for idx in inputs[0]["frame_idx"]]
      img_shape = outputs['image_size']
      pan_seg_result = outputs['pred_masks']
      segments_infos = outputs['segments_infos']
      segments_infos_ = []
     ...Rest of the code....