-
Hello fg-midee & charlesmindee,
The End to end ocr named doctr developed by you is fantastic.It is very easy to use and have very good results.Currently i am working on ocr related project.I had impl…
-
I've been discussing (with @andrrizzi @SimonBoothroyd @j-wags @proteneer) the potential for solving a number of technical debt issues we have accumulated with a new Python container class to represent…
-
I ran into a problem when computing the Taylor series of the differentiable function `f` whenever `α` is an integer. Simply rephrasing the function using `inv` and positive powers of `α` solves the pr…
-
## 🐛 Bug
Grad on `torch.symeig` gives the wrong value if there are repeated eigenvalues (degeneracy exists), even though the grad should be finite.
## To Reproduce
```python
import torch
to…
-
When having a look at the implementation and looking at the differences with `torch.householder_product`, I found a weird thing.
At the moment, when called with a tensor of the form `hh = param.tri…
-
We are a group of researchers and engineers who have interest int underwater acoustic geolocation (analogous to LBL) and potentially tomography.
We would thus need to perform modeling in spatially (d…
-
## 🐛 Bug
(pardon my posts from a few days back about memory leak, I'm in the middle of hunting memory leaks in my applications)
I extended PyTorch with `torch.autograd.Function` to write the gradi…
-
This line https://github.com/facebookresearch/barlowtwins/blob/main/main.py#L208 use `torch.distributed.all_reduce` to sum the correlation matrices across all gpus. However as I know this op is not de…
-
## Reason
`ComputeMeanThermalExpansionFunctionEigenstrain` computes a temperature derivative of alpha. However, we can easily end up at a non-differentiable point in the thermal expansion function, f…
-
Hello,
I am trying to use HOOMD-TF to evaluate forces in a system of rigid subunits, composed of 3 particle types, as well as a scaffold particle. The final goal is to implement an attractive force…