AttributeError: type object 'Variable' has no attribute 'chunk'

[MrLinNing]

hello, @tbung
My Pytorch version is 0.4.0, cuda version is 9.0 and python is 3.5.
But when I run this command:

python train_cifar.py --model revnet38 --clip 0.25

Problem happened:

File "pytorch-revnet/revnet/revnet.py", line 191, in _grad 
        dy1, dy2 = Variable.chunk(dy, 2, dim=1) 
AttributeError: type object 'Variable' has no attribute 'chunk'

Can you help me to fix the bug? Thank you.

[tbung]

Hi @MrLinNing,

this bug is due to the fact that this code was written when pytorch 0.4 was not released yet, and a bunch of stuff changed since then, as described in the migration guide.

I will try and fix all related issues, but I currently have other stuff I need to work on, so it might take some time.

You can of course try and fix all related issues by yourself, your bug should be resolved by replacing Variable.chunk with torch.chunk. Pull requests are very welcome if you do!

Thanks for your interest and patience!

Cheers,
Till

[tbung]

This has been closed by @JuanFMontesinos in #8.