-
#### Describe the bug
After creating a sparse tensor using the `sparse` library as per the example in the [documentation](http://tensorly.org/stable/user_guide/sparse_backend.html), I cannot pass…
-
### 🐛 Describe the bug
I have encountered a numerical stability issue when using torch.linalg.cholesky_ex to compute the Cholesky decomposition on GPU.
```
import torch
import numpy as np
from…
-
#### Summary
I would like to perform a non-negative CP tensor decomposition where I set the `normalize_factors` parameter to True, but am unable to do so as I receive errors in both the `non_negati…
-
When I testing the acceleration effect on CPU by decomposing convolution layers, I found pytorch is slow and cannot utilize multicores of CPU.
```
# To blind GPU
os.environ["CUDA_VISIBLE_DEVICE…
-
Hi,
There seems to be an issue in the tensor contraction when using the separable Fourier convolution option (`separable=True`).
The problem occurred when I tested the `plot_FNO_darcy.py` example …
-
Thank you so much for creating such a great tool! Bento is exactly what I’ve been needing, and I’m really excited to get started with it.
I’ve been trying to use it with my own Xenium data, but I kee…
-
I don't understand why the unfold function is different from Kolda's. Is there any benefit? If I make a small change to unfold, such as order='F', it becomes Kolda's and my code gives very different r…
-
Since the `SpectralConv` refactor, we now depend on newer source from `tltorch` than is available in the latest tagged release on PyPI. Instead of installing `tensorly-torch` from pip, to pass all tes…
-
I am trying to recreate the PARAFAC demonstration in the [JOSS publication](https://www.theoj.org/joss-papers/joss.04754/10.21105.joss.04754.pdf) (and the labelled decompositions [tutorial](https://te…
-
#### Describe the bug
Decomposing a 2D tensor along both modes, while specifying two ranks results in an error because internally there's a tensor created on the CPU as part of the process, which can…