Closed Dariushuangg closed 8 months ago
Thank you for the issue. It appears to be an oversight on my part. I will promptly implement the necessary changes and provide an updated benchmark using the VGG model.
Code has been updated and I will close this issue.
Hi, thanks for sharing your implementation. I noticed that in your
CAM
class, you are using two separate networksself.linear_max
andself.linear_avg
to process max pooled feature and average pooled feature. This differs from other implementations and the original paper, which said:Do you have a specific reason for this design? or is this an oversight? Thanks!