Closed dlyldxwl closed 3 years ago
Hi @dlyldxwl,
Thank you for pointing (1.) out. The non-native CUDA functions have not been updated for a while. I'll include this in the latest commit. Do note that you are encouraged to use the CUDA-native versions CUDA_SOFTPOOLxd for better performance. The in-place alternatives are less stable by nature.
As for using SoftPool for vectorisation, we have not tested this as the paper was focusing on sub-sampling image/video regions. But you can of course try it out yourself. I would be interested in the results as well if you do!
Best, Alex
Thank you for your sharing~ However I have some doubts,
this code represents the weight value is calculation by using channel dimension on the same spatial position, rather than applying spatial region? https://github.com/alexandrosstergiou/SoftPool/blob/7cd12c72b7096bc70d136e6b001eb2c338461bb2/pytorch/SoftPool/idea.py#L181
for the last pooling layer, global avg pooling is better than softpool?
Looking forward to your reply