Issue in reproducing evaluation results with sparse rcnn checkpoint
ihjasahammedm opened this issue · 2 comments
First of all thank you for releasing the code and ckpts.
I am not able to reproduce the results using config file "sparse_rcnn_focalnet_tiny_fpn_300_proposals_crop_mstrain_480-800_3x_coco_lrf.py" and it's corresponding checkpoint given in readme. The code itself is showing that there is mismatches in state dictionary.
For this to run I also had to update the line 1 in config from _base_ = '../_base_/sparse_rcnn_focalnet_fpn.py' to _base_ = '../_base_/models/sparse_rcnn_focalnet_fpn.py'
The metrics obtained are very low and close to zero!
Following is the command I used to run the evaluation:
python tools/test.py configs/focalnet/sparse_rcnn_focalnet_tiny_fpn_300_proposals_crop_mstrain_480-800_3x_coco_lrf.py ckpts/focalnet_tiny_lrf_sparsercnn_3x.pth --eval bbox
Following is mAP values obtained:
Could you please look into this and let me know if I am doing something wrong here?
thanks for your interest!
I will take a look on it.
I think in the config section there are no configs relevant to modulation based bbox_head. The one you have evaluated is attention based one. Those files are missing!