-
There are problems with the Graphviz plotting of the computation graphs in `autodiff`:
- [ ] The nodes don't indicate the operation that took place (e.g. `+`, `sin`).
- [ ] There are double links …
avhz updated
7 months ago
-
MWE:
Running one of the tests in `NNODE_tests.jl`,
```julia
using Flux
using Random, NeuralPDE
using OrdinaryDiffEq, Statistics
import OptimizationOptimisers
Random.seed!(100)
# Run a…
-
## Description
There are lots of functions that don't have reverse mode specializations.
#### Matrix operations
All of these would be very useful, espcially the basic arithmetic of the firs…
-
**Concisely describe the proposed feature**
Currently, the autodiff system only supports Taichi field. However, there are some limitations of field such as the number of snode trees is limited which …
-
I'm a newbie using the autodiff library and more general using automatic differentiation in general. I was trying to implement gradient computation for a simple Gauss-Seidel type solver. It runs fine …
-
## Summary
Hi,
I developed a custom sphere tracer and wanted to forward a single parameter to the rendered image.
dr.set_grad(p, 1)
dr.forward_to(image)
The cu…
-
The following minimal example produces a stack overflow:
```
// C++ includes
#include
// autodiff include
#include
#include
using namespace autodiff;
// The scalar function for which th…
-
**Describe the bug**
Starting in roughly July, synthesized TangentVectors for Differentiable types can no longer be extended. Initially, these caused an assertion failure, then an error for a circula…
-
| | |
|------------------|-----------------|
|Previous ID | SR-15823 |
|Radar | None |
|Original Reporter | @philipturne…
-
**Describe the bug**
Running the text classification example's ag news training step on multiple discrete GPUs fails with "Shader validation error":
- [stacktrace.log](https://github.com/tracel-ai…