Support CAM based method for model interpretability

[iumyx2612]

Describe the feature

Motivation A clear and concise description of the motivation of the feature. I want to know why my experiments fail

Related resources Pytorch grad-cam: https://github.com/jacobgil/pytorch-grad-cam
MMDetection implementation using Pytorch grad-cam: https://github.com/open-mmlab/mmdetection/pull/7987
MMDetection one still WIP but I can use many Grad-free CAM

Additional context

[MeowZheng]

it's much appreciated for it. We are looking forward to this feature