Seyyed Hossein Hasanpour

@angelamin ,@LXWDL: Did you solve this issue? I'm facing the very same error. I'm on pytorch 0.3.1

@naranglovish : Use [this port](https://github.com/Eric-mingjie/network-slimming) instead.

@RichardMrLu : how did you run the script with version 0.4? Can you share your changes?

@engmubarak48 @ankitnamdeo34 , @sybrin-innovations any update guys?

Here you are : https://github.com/foamliu/InsightFace-v2/releases

I have. in my case I had used pytorch 1.4.0 and 1.5.1 successfully without any issues. I haven't tested with `1.3` though! also `1.6.0` didnt work for me either, after...

I'm speaking from my own experience. all packages and modules seem to be fine with any newer version except torch . till 1.5.1 everything works well. but since 1.6.0 this...

you need to use `.module` attribute when your model is wrapped in a DataParallel objetc

What is it that you are doing that causes this error? by the way, last time I checked 1.5.1 was working fine and 1.6 caused my loss to go to...

you can access them here https://github.com/foamliu/InsightFace-v2/releases