Waleed Abdulla
Waleed Abdulla
> Folding conv3x3 and conv1x1 That looks like a bug in the `FoldDuplicates` transform. Thanks for the report. I’ll work on it, but in the meantime if you want a...
> I would be happy to talk more, since there is an overlap in interests and approaches. Vide my > https://github.com/stared/livelossplot package (did you take any inspiration from it?) I...
@stared Yes, happy to talk about it. I'll DM you.
Are you sure you're feeding tensors of the correct data type? It seems to be complaining that it's receiving Long when it's expecting a float.
HiddenLayer is designed to take either a TensorFlow or a PyTorch model. Are you passing a FastAI object instead? That might be the issue.
This would be a useful feature. It's not available right now, but you can probably do it with a bit of additional code. I'll tag this issue as an enhancement...
You can remove the constant using the transform: `Prune("Constant")`. I don't know the rules you have in place already, but based on the image you posted I'm guessing you have...
Thanks for the report. Admittedly, I haven't tested with RNNs. Would you mind sharing the sample code used to generate this?
@AutuanLiu I want to give an update on this. Thank you for raising the issue and providing details. And sorry it took a long time. I ran experiments with LSTMs...
@Cpruce Thanks! This is a great addition. I'm starting to review the code. In keeping with the goal of keeping the repo small and light, I'd suggest removing anything that...