-
It would be great to factor out the testing machinery that checks consistency of all the kinds of derivatives and gradients and all kinds of computing the value of the objective function.
Ideally, …
-
[Graph Convolutional Networks](http://tkipf.github.io/graph-convolutional-networks/).
-
In my current knowledge, appending the training loss to a list inside `gradient() do end` does not work since `push!` is non-differentiable. My current workaround is recomputing the whole training los…
-
This is to upgrade to Python 3.8.x.
- [PEP569 -- Python 3.8 Release Schedule](https://www.python.org/dev/peps/pep-0569/)
- [What's new in Python 3.8](https://docs.python.org/3.8/whatsnew/3.8.html)
…
-
# Design
We created the next generation map format for Autoware (called Autoware Maps Format).
### Goal
- Make map format open format
- Make common format of Autoware and [AMS](https://github…
-
Example: https://mila.quebec/en/publications/
It would be nice to reuse the same code as in the Mila website. Not sure if that's 'easily' possible via RTD
-
Hello,
I'd like to report a possible bug I encountered when computing Hessians of functions involving jax.numpy.linalg.norm.
If the input is different from zero, results are OK, however, if the He…
-
Hi Dan, I'm Alejandro Suárez Mascareño, we spoke at the Oxford GPRV workshop.
Yesterday I started playing around with Exoplanet/Pymc3 following your recommendation. First of all I want to say I'm …
-
### Problem
After inputting the unnormalised raw counts, I try to train the regression model using adata_ref. However, it gave back ValueError.
### the data input
adata_ref.X
### the para…
-
First of all, I need to tell you that I am a beginner in programming.
In my differentiable rendering experiment, I want to input the reference image externally, without having to render it in Mitsu…