Chandan Singh

Thanks for the interest! We haven't yet tried CD for TreeLSTMS and aren't sure what the correct equations should be. I'd suggest starting with the equations in Sec 3 of...

I have the same issue - I believe it is related to Jupyterhub specifically. When I run jupyterlab from jupyterhub I get the issue, but when I connect to it...

To get it to work I changed the final conv layer of the Generator to: `nn.ConvTranspose2d( ngf, nc, kernel_size=1, stride=1, padding=0, bias=False)` and the final conv layer of the Discriminator...

Agreed this is a simple fix that should be implemented! I made a quick fix at [this repo](https://github.com/csinva/interpretability-implementations-demos) in the meantime. It's runnable with `pip install git+https://github.com/csinva/interpretability-implementations-demos` and then `from...

I haven't yet. As of now, am planning on just linking the repo url.

Thanks for your interest @abhishek-ghose! Sorry you've had a hard time replicating the result...not sure I see any blatant error with your code. @aagarwal1996 - could you point Abhishek here...

+1!!!

@OmerRonen @aagarwal1996 Can either of you take a look? Sorry I'm busy with the new job but don't want to leave Nick hanging. Would be really awesome to have HSTree...

@aagarwal1996 @yanshuotan Can someone add in sample-weight support for HS?

Agreed, thanks Yan Shuo for adding HS `sample_weight` as an explicit argument in https://github.com/csinva/imodels/pull/156. Should work now @kmedved!