wangzixiang
/
lerobot
mirror of https://github.com/huggingface/lerobot.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[pre-commit.ci] auto fixes from pre-commit.com hooks 

for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2025-03-19 05:58:57 +00:00
parent 3c5bb6b0d6
commit 15c9ecdf52
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lerobot/common/policies/dexvla/README.md
View File

@ -2,7 +2,7 @@
DexVLA: Vision-Language Model with Plug-In Diffusion Expert for Visuomotor Policy Learning</h1>
This policy is Community Contributed. For more information about DexVLA, you can also refer to [this](https://github.com/juruobenruo/DexVLA).
This is [project website](https://dex-vla.github.io/).
This is [project website](https://dex-vla.github.io/).
## Dataset
### Data format
@ -141,4 +141,4 @@ python lerobot/scripts/eval.py \
~~~
### Inference Speed
Tested on a single A6000 GPU, the DexVLA could infer 3.4 action chunks in one second. For each action chunk, if we execute 25 actions, the real control frequency can be 85 (3.4*25)Hz.
Tested on a single A6000 GPU, the DexVLA could infer 3.4 action chunks in one second. For each action chunk, if we execute 25 actions, the real control frequency can be 85 (3.4*25)Hz.