Open willcray opened 9 months ago
We were using Mask Scoring RCNN in 2.x. Upgrading now. Noticed there are no longer configs for using mask scoring rcnn. No longer supported?
We were using Mask Scoring RCNN in 2.x. Upgrading now. Noticed there are no longer configs for using mask scoring rcnn. No longer supported?
There are configs in mmdet 3.0+ here
Did you end up getting it working in 3.x ?
Did you end up getting it working in 3.x ?
I can use a MaskScoringRCNN model, but I can't access its mask scores.
In training I am seeing an error:
2024-02-08T20:45:39.643Z | File "/opt/conda/lib/python3.10/site-packages/mmdet/models/roi_heads/standard_roi_head.py", line 140, in loss
-- | --
| 2024-02-08T20:45:39.643Z | mask_results = self.mask_loss(x, sampling_results,
| 2024-02-08T20:45:39.643Z | File "/opt/conda/lib/python3.10/site-packages/mmdet/models/roi_heads/mask_scoring_roi_head.py", line 141, in mask_loss
| 2024-02-08T20:45:39.643Z | loss_mask_iou = self.mask_iou_head.loss_and_target(
| 2024-02-08T20:45:39.643Z | File "/opt/conda/lib/python3.10/site-packages/mmdet/models/roi_heads/mask_heads/maskiou_head.py", line 142, in loss_and_target
| 2024-02-08T20:45:39.643Z | mask_iou_targets = self.get_targets(
| 2024-02-08T20:45:39.643Z | File "/opt/conda/lib/python3.10/site-packages/mmdet/models/roi_heads/mask_heads/maskiou_head.py", line 193, in get_targets
| 2024-02-08T20:45:39.643Z | area_ratios = torch.cat(list(area_ratios))
| 2024-02-08T20:45:39.643Z | File "/opt/conda/lib/python3.10/site-packages/mmdet/models/roi_heads/mask_heads/maskiou_head.py", line 240, in _get_area_ratio
| 2024-02-08T20:45:39.644Z | ratio = gt_mask_in_proposal.areas[0] / (
| 2024-02-08T20:45:39.644Z | IndexError: index 0 is out of bounds for axis 0 with size 0
Hello, I was happily using mmdet 2.28.0 and the Mask IoU / Mask Quality scores outputted by the mask_iou_head in the the Mask Scoring RCNN model. I recently upgraded to mmdet 3.0, and now the output of the inference_detector doesn't include Mask IoU scores. The output is a DetDataSample whose pred_instances only contain bbox, scores (for the bounding boxes), labels, and masks. There is no mask scores / mask quality scores / mask iou scores field.
How do I use models that output mask iou scores within the new context of a DetDataSample?