Eugene Mironov
Eugene Mironov
@xianglunkai Hello, thanks for your comment. Regarding the first question - `inference_delay computation is not right?` - why so? The inference delay is calculated in the context the inference steps,...
People use super diverse setups, if u have stable connection to robot, good enough processor and the right GPU, the `max` approach will work fine.
In case more basic env setup - p95 should work better.
Hey, it's merged into the main, but maybe haven't released yet. Check the repo
https://github.com/huggingface/lerobot/blob/main/src/lerobot/policies/rtc/modeling_rtc.py
Also, here is an adjustment - https://github.com/huggingface/lerobot/pull/2499. I need to make comprehansive testing, will do it in the next several days.