linyq2117/CLIP-ES

Reproducing miou 58.6 (Initial) from Table 2

Closed this issue · 2 comments

I am very grateful for your solid open-source work. I've encountered a slight issue while trying to reproduce the 58.6 metric mentioned in Table 2. I directly used 'cam_to_refine' as the value for 'cam_refined' and then executed 'eval_cam.py' to evaluate the CAM (Class Activation Maps). However, the resulting mIoU I obtained is 50. Could you please help me identify what might be causing this discrepancy?

Thanks for your interest.

You need to use highres_cam to reproduce 58.6 because cam_refined is not scaled to the original resolution. You could simply uncomment highres in line 212 and set --cam_type highres when executing eval_cam.py.

I have successfully achieved the result. Thank you very much for your response.