Thomas Lips

I changed the orientations [here](https://github.com/tlpss/mujoco_menagerie/tree/main). Do you want to add a site/body that corresponds to the frame of the controlbox as well? because now the `base body` 's frame does...

@ExtReMLapin you need to match the feature config to the actual model. So for example, for your model the feature config is (taken from the [docs](https://huggingface.co/timm/maxvit_small_tf_512.in1k#feature-map-extraction) ): ``` for o...

@aliberts, I stumbled upon this problem and could not find it in the readme? Could you make it more explicit?

@AbdElrahmanMostafaRifaat1432, I have not used the aloha format but I created a [script](https://github.com/tlpss/lerobot/blob/dp_zarr_dataset/examples/port_datasets/dp_3d_zarr.py) to convert datasets using the format from the diffusion policy codebase. THe process for the aloha format...

@AbdElrahmanMostafaRifaat1432, that is convenient! > I wonder if there is a solution to convert data immediately locally instead of pushing it to hugging face and taking it again from hugging...

and this would also require dealing with the new class [here](https://github.com/gramaziokohler/roslibpy/blob/db741a630880bc5fa33db5e66b44dc6bd032be5b/src/roslibpy/core.py#L134)

@andlyu how did you end up doing this?

FYI: implemented in #831

> `lerobot/examples/4_train_policy_with_script.md` guides users to point CLI arg `config_path` to the directory containing the train_config.json file rather than the json file itself which doesnt work. > > Put explicitly, >...

Hi @vmayoral Thanks for your thoughts. I indeed was thinking about how to use data collected using the Gello codebase for training policies in Lerobot. (*a posteriori* integrating gello with...