You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, impressed by your block squeezing and block linearization idea, but the memory usage of bn implemented by pytorch is some kind of weird, which is not IN-PLACE, which allocates an input tensor size memory buffer for output, thus doubles the memory consumption. please refer to https://github.com/pytorch/pytorch/blob/master/aten/src/ATen/native/cudnn/BatchNorm.cpp so i think your comparison is not fair, to some extent.
The text was updated successfully, but these errors were encountered:
Thanks for your interest WangS! I agree that in-place BN layers are more memory-efficient. When we were conducting this work we followed the implementations of Ding etal's and didn't take in-place BN layers into consideration, neither in DBB/RepVGG nor ours. This surely leads to higher extra memory to a severer extent for DBB. However, I could not provide results for in-placed variants currently since I am working on some other projects now.
Hello, impressed by your block squeezing and block linearization idea, but the memory usage of bn implemented by pytorch is some kind of weird, which is not IN-PLACE, which allocates an input tensor size memory buffer for output, thus doubles the memory consumption. please refer to https://github.com/pytorch/pytorch/blob/master/aten/src/ATen/native/cudnn/BatchNorm.cpp so i think your comparison is not fair, to some extent.
The text was updated successfully, but these errors were encountered: