Kun Li

Hi @luisenp , Thank you for your advice. I have tried to change the default sum of squares to just sum of error vector. I can get the negative cost...

There's not error happened when I tried `LevenbergMarquardt `. I have tried [DCEM](https://github.com/facebookresearch/theseus/blob/main/theseus/optimizer/nonlinear/dcem.py) and it looks not optimization happens. It only shows the 0th iteration error and not any further...

@luisenp Here's the output using DCEM. It only has 2 steps optimization when I change the `error_metric_fn` from the default metric to `error_sum_fn` in the `th.Objective`.

Hi @luisenp, thanks for the quick fix. It works now and can generate some optimization after 50 iterations. However, it looks not easy to find a good solution after i...

Thank you for your tips using `DCEM`. I have increase `max_iterations` from 50 to 100 and also using `n_elite=10`, `init_sigma=5.0`. However the error does not looks like having the right...

Thank you for replying. Does the latest PyTorch nightly is the same as PyTorch 2.0?

Hi @zou3519 , I have tried PyTorch 1.13.1, it's still the same error. `RuntimeError: data.find(layerId) == data.end() INTERNAL ASSERT FAILED at "../aten/src/ATen/functorch/DynamicLayer.cpp":256, please report a bug to PyTorch. ` I...