openpi
openpi copied to clipboard
Physical-Intelligence
I'm trying to run the server of ALOHA sim but get this error: INFO:openpi.shared.download:Downloading s3://openpi-assets/checkpoints/pi0_aloha_sim to /home/yfx/.cache/openpi/openpi-assets/checkpoints/pi0_aloha_sim 100%|████████████████████████████████████████████████████████████████████████████████████████████▉| 11.2G/11.2G [04:47
Hi, Thanks for your excellent work! I have some questions about the representation of proprioception observation space and action space during training. 1. In the paper, you mentioned using the...
hello,I want to finetune pi0_base on my machine,but i only have 48G GPU memory,if there any setting allow me use grad accumulation?
hi, guys, this is a great job. Thank you for opening up PI0, physical intelligence. I want to run pi0 in one robot. Here are what i have. 1.robot =...
The cv2.imdecode function returns a BGR image, but it seems there is no conversion to RGB after decoding. As a result, when reading the PNG image bytes from the Parquet...
Hi, In the pi0 paper, it is mentioned that the state information during model training is joint poses. The tuning examples provided in this repository also use joint pose, except...
Hi, I run policy inference part in examples/inference.ipynb successfully. Now I get an 2-dim array. However, I have no idea how to visualize the result action as real robot manipulation....
Hi, really impressive work! and thanks for generously open-sourcing the codebase and pretrained models. I was wondering why ACT and DP performed poorly in the Pi0 Paper VI C experiment,...
Hi, I would like to ask if I want to fine-tune the ur5 robot using the pi0-base model or pi0-fast model, how do I fine-tune it? What is the data...
Thank you for your great work! When I follow the steps [here](https://github.com/Physical-Intelligence/openpi/blob/main/examples/aloha_sim/README.md#without-docker) to setup the Aloha Sim environment, I encounter this error. Please guide me to fix it. 
