-
I want to construct a neural network in pytorch which outputs appropriate values of mujoco model parameters. But this requires that mujoco model parameters are converted into pytorch tensors and mujo…
c4cld updated
2 years ago
-
## 🐛 Bug
`torch.nn.functional.kl_div` fails gradgradcheck if the target requires a gradient.
## To Reproduce
```python
import torch
from torch.autograd import gradgradcheck
from torch.nn.f…
-
Hey TF,
Trying to integrate the new Unitary RNN's into tensorflow. Unfortunately, they require Fast Fourier Transform and Inverse Fast Fourier Transforms.
For efficiency this needs to be done on th…
-
Hi,
I am trying cell2location for my data.
followed the tutorial and got an error at estimation of reference signature.
here is execution code.
My computer has only cpu, I do not use gpu opt…
deryu updated
2 years ago
-
## 🚀 Feature
Implement derivative for [`torch.lstsq`](https://pytorch.org/docs/stable/torch.html?highlight=lstsq#torch.lstsq). Backward pass currently raises `RuntimeError: the derivative for 'lstsq'…
-
Song Y, Song J, Ermon S. [Accelerating natural gradient with higher-order invariance](http://proceedings.mlr.press/v80/song18a/song18a.pdf).
-
before adding these:
1. check that they are valid papers that use deal.II
2. check that they are not already in the .bib files.
3. fix up the publication
```
@Article{Schutz2018,
author = {S…
tjhei updated
2 years ago
-
Latest: tensorflow master 2.2.0. It was working until 2.1.0 from what I remember.
**Regression in model.optimizer.get_gradients()**
```python
import numpy as np
from tensorflow.ker…
-
### 🐛 Describe the bug
`xlogy` returns wrong gradient when `input` is 0. Since it is continuous and differential at the point 0, it shouldn't return 0 as the gradient.
```py
import torch
def f…
-
I'm curious what type of functions one should be able `grad` over. i.e. what is the implicit restriction on `a`
`def grad (f:a->Float) (x:a) : a = snd (vjp f x) 1.0`
Currently it seems to work f…
srush updated
2 years ago