Lorenzo Porzi

Can you try again with the latest version of the library? We were (rarely) encountering similar issues before `v1.0.0`, but not anymore after the update.

This looks like a python module resolution issue. I would suggest to try again with the latest version of the code, since the scripts / library structure has been reworked.

I tried reproducing the issue on my machine with no success (just run a forward / backward sequence on CPU). Can you please come up with a minimal reproducing example...

@TuringKi Is this after training the model or before?

@TuringKi does the same happen also with standard BN from Pytorch, or just InPlaceABN?

@TuringKi I'm struggling a bit with pinpointing your problem, I'll need to ask a few more questions: 1) Are you training with InPlaceABN and testing with InPlaceABN, or taking a...

Can you try again with the latest version of the library (`v1.0.2`)?

@vakkov thank you, please let us know about your findings! **Note**: reproducing the results in "In-Place Activated BatchNorm for Memory-Optimized Training of DNNs" by training your own models is beyond...

This is not a trivial task, unfortunately. It has been on our radar for a while, but we can't promise anything for now.

@MendelXu the code for #4 has moved here: https://github.com/mapillary/inplace_abn/blob/master/inplace_abn/functions.py#L136 Anyway, the error you are reporting is probably not connected to that, as the 1th output of `InPlaceABNBackward` mentioned in the...