aditya

I'd like to extend the hidden Markov model implementation so that it can handle transition matrices that are very sparse. For my usecase, I'd like to extend it such that...

[Potential Bug] in wav2vec (1.0?): targets always zero, loss computation potentially incorrect?

3

## 🐛 Bug wav2vec (the og one) from the [wav2vec readme]( https://github.com/facebookresearch/fairseq/blob/main/examples/wav2vec/README.md#wav2vec), when called, as I understand, should return the contrastive predictive logits from the paper that are used to...

[FR] Adding Gaussian Process Latent Variable Model Examples

1

#### Summary: I'd like to add examples of GPLVMs to the docs. A classical GPLVM (as described in Lawrence, N. D. 2003, Gaussian process latent variable models for visualisation of...

B.eye doesn't support tensors on cuda

1

`eye` doesn't keep tensors on the gpu: ```python In [1]: import lab as B In [2]: import lab.torch In [3]: import torch In [4]: B.eye(torch.ones((2, 2)).cuda()) Out[4]: tensor([[1., 0.], [0.,...

Function registration with lab + plum 2.0

2

With the previous versions of plum and lab (`backends==1.4.32 plum-dispatch==1.7.4`), the following was a way in which one could register a new set of types for a function: ```python import...