mAP of the converted cascade rcnn model drops
Opened this issue · 0 comments
BaiSh0707 commented
The project is a great job. We successfully converted the cascade rcnn model and increased the inference speed. But the mAP of the model on coco drops from 45 to 41.9 after the conversion for both fp32 and fp 16 setting. Could you please tell us where is the problem may be? Thanks. @grimoire