-
Recently **autonomous driving** is linked with the concept of **data closed loop**, because it is widely acknowledged that development engineering of autonomous driving is to solve a “**long-tail prob…
-
At training time, once you apply Gumbel softmax on the patch selection logits, you have 2 numbers for each patch - the probability of keeping it, and the probability of discarding it.
Do you actually…
-
This ticket implements parallelization of basic operations (arithmetics, contractions) on tensors on free modules of finite rank. The parallelization is performed by means of Python's module `multip…
-
*Please add one of the following label to your issue's title, and delete this section:*
- [🐛 jit_flush_malloc_cache(): Dr.Jit exhausted the available memory and had to flush its allocation cache to…
-
Is it possible to use gradient checkpointing with higher? Thanks
-
This ticket modifies `DifferentiableManifold.vector_frame()` to allow for constructing a vector frame from a spanning family of linearly independent vector fields:
```
sage: M = Manifold(2, 'M')
sa…
-
We should fix it. Not quite sure how though.
https://gist.github.com/zou3519/73a6189e21561f6ef5b42874e8a4826f
-
I've noticed that in addition to the Hessian regularization in DDP, you describe and implement a line-search for the scaling of the feed-forward term of the controller.
I am aware that Mayne (1967…
-
Currently we define the objective over the model, which looks like
```python
tt = torch.tensor
differentiable_module: nn.Module = None # any differentiable model
differentiable_objective: Call…
-
## 🚀 Feature
Why not implement some common metrics, to evaluate models, with strong GPU acceleration.
## Motivation
When I need to evaluate model accuracy (ex. measure r squared) I have to writ…