Jacob Austin

Hi Lilian. Thanks for creating the issue and pointing this out. I just timed it myself and got close to the same as you (1 minute, 19 seconds). I think...

Hi @Naereen thank you for following up. I apologize for the delay. Started a new job recently which has kept me busy, and Coral hasn't been under active development. I've...

Our text code was recently open-sourced here: https://github.com/google-research/google-research/tree/master/d3pm/text.

Thanks for asking, I agree the description is ambiguous. We'll update the paper and README. Task IDs 11-510 are the 500 test problems. We use 90 problems (511-600) for validation...

I ended up using ```python transform = tfs.Compose([ tfs.TriangleMeshToVoxelGrid(resolution=30), ]) # Setup Dataloader train_set = kal.datasets.ModelNet(root=args.modelnet_root, categories=args.categories, transform=transform) dataloader_train = DataLoader(train_set, batch_size=args.batchsize, shuffle=True, num_workers=8) ``` which works fine after you...

Running "pip install nuscenes-devkit" works. It looks like nuscenes was removed from PYPI.

Any updates on this? I'm happy to help if there's anything I can do. As you probably know, syntax files for .mly and .mll files were created in the old...

The lower-case `discrete` function needs to be the only way of building Discrete objects. So all Discrete tests need to be changed to use this method. I think you will...

What version of CUDA did you install? Also what GPU do you have? CUDA is failing on an old sm_20 architecture (Fermi, which is an old GPU model). You could...

So this seems like an issue with the CUDA installation itself. Are you able to run nvcc from the command line? Or install other gpu based software like pytorch/tensorflow? There...