New adaptive pooling layer.
CielAl opened this issue · comments
CielAl commented
It appears that models in the torchvision are now using adaptive poolings: adaptive_avg_pool2d
to break the tie to the input size: vision/densenet.py
Perhaps that simplify the constructor a little bit and generalize the usage even more?
Geoff Pleiss commented
That sounds good. Would you be willing to put up a PR?