Closed PengtaoJiang closed 2 years ago
@PengtaoJiang , Thank you for sharing your great work! I will read the paper and attempt to implement it!
However, before that, I have a question to ask about the license of LayerCAM just in case. When our users commercially use LayerCAM via tf-keras-vis without getting permission, is this case a license violation? If so, please do NOT allow us to incorporate LayerCAM into tf-keras-vis. Because tf-keras-vis's license is MIT and we want our users to use it without worrying about whether it's commercial or not.
Thanks!
Thanks for reminding me. I remove the license limit. Any user via your popular repository will not wrong about the license limit.
@PengtaoJiang , Thank you for your quick response! I'm grad to hear that.
@PengtaoJiang , I'm sorry for the delay to implement it.
I've now merged LayerCAM
module to master
branch. It will be released as v0.8.0
in a few days.
All the best!
If the code I implemented has any problem, please let me know.
Hi, @keisen , Our paper "LayerCAM: Exploring Hierarchical Class Activation Maps for Localization" is accepted by TIP recently, which can visualize the class activation maps from any CNN layer of an off-the-shelf network. Could you add our method to your popular repository for more people to try this method? Our method is a simple modification of Grad-CAM. It should easy to implement. Here is the paper and code. Hope for your reply.