Kun Li

Code for Point-to-Voxel Knowledge Distillation

2

Congrats! Is there any plan to release the code for Point-to-Voxel Knowledge Distillation except vanilla training code?

Thank you so much for such elegant and great work. May I ask when will the code be released?

Can't load scenario using cached data?

4

Hi, Thank you for such wonderful repo. I just found there might be issues when I use create_scenario_from_paths.py to load cached data. First, at https://github.com/motional/nuplan-devkit/blob/update-devkit-v0.4/nuplan/planning/script/builders/scenario_builder.py#L179, the log_name seems to path.parent.name...

Not having the comparable optimization result with Theseus compared to CasADi?

9

## ❓ Questions and Help I'm currently using CasADi with the following parameters: ``` optimizer.solver("ipopt", {"ipopt.print_level": 0, "print_time": 0, "ipopt.sb": "yes", "ipopt.max_cpu_time": 0.35}) ``` Its optimization error log looks like...

Can theseus return negative cost?

13

## ❓ Questions and Help Hi theseus team, I'm currently using theseus to solve some non-linear optimization problem. In my case, some cost function will return negative cost. However, in...

INTERNAL_ASSERT failed

4

`RuntimeError: data.find(layerId) == data.end() INTERNAL ASSERT FAILED at "/__w/functorch/functorch/functorch/csrc/DynamicLayer.cpp":251, please report a bug to PyTorch. '` Hi, I have used `vmap(jacrev(jac_fn, argnums=0))(*args)` to calculate some jacobians, and the above errors...