3 eval and train data format mismatch

octo-models / octo

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

https://octo-models.github.io/

MIT License

787 stars 152 forks source link

3 eval and train data format mismatch #127

Closed mateuszwyszynski closed 3 weeks ago

mateuszwyszynski commented 3 weeks ago

This should fix the mismatch between proprio state data values during training and evaluation. Code to generate the single examples for which one can easily compare the values can be found in the corresponding issue