Cedric Luo
Cedric Luo
Please provide the information generated by `python mmdet/utils/collect_env.py`. In lastest version mmdet v2.25.1, auto-resume is suupported, see https://github.com/open-mmlab/mmdetection/blob/3b72b12fe9b14de906d1363982b9fba05e7d47c1/tools/train.py#L32.
@nacayu That's strange. Please try to load other checkpoints.
See https://github.com/open-mmlab/mmcv/pull/1108. https://github.com/open-mmlab/mmdetection/issues/5505 Please update mmcv to v1.3.18.
Could you provide some evidence to illustrate that?
Please provide the traceback information.
@Vo-Linh Which config file did you use? And did you make any modification to code and config?
The error is from here, https://github.com/open-mmlab/mmdetection/blob/3b72b12fe9b14de906d1363982b9fba05e7d47c1/mmdet/datasets/pipelines/transforms.py#L1117 gt_bboxes.shape or gt_bboxes_ignore.shape is (0, ) wihch means that there is no annotation in the current image. So please check that whether there exists...
Question 1: I suggest that convertef you dataset to coco format, refer to https://mmdetection.readthedocs.io/en/latest/tutorials/customize_dataset.html. Question 2: For instance segmentation, num_stuff must be 0, and num_thing = 1 due to (num...
Yes, better to be `_get_targets_single`
@jackkwok You can use batch_size = 8 * 1 and scale the lr due to V100 16G. For batch_size=8 * 2, 19 GB is required, see https://github.com/open-mmlab/mmdetection/blob/3b72b12fe9b14de906d1363982b9fba05e7d47c1/configs/mask2former/metafile.yml#L212