Closed yanrihong closed 2 weeks ago
Thank you for your kind words!
Correct. For example, if you want to train VoxAct-B on Open Jar, you can use these scripts, documented on README:
./train_open_jar_ours_vlm_10_demos_v2_11_acting.sh
./train_open_jar_ours_vlm_10_demos_v2_11_stabilizing.sh
We used Ubuntu 22.04. It took two days to train one acting policy and one stabilizing policy in parallel (two separate GPUs).
Yes, but it would be slower since you would train the acting and stabilizing policies on a single GPU.
The acting and stabilizing policies are based on the PerAct architecture, but we only use 50^3 voxels instead of the 100^3 voxels used in PerAct, so training VoxAct-B is much faster than training PerAct. Please refer to the Appendix for more details.
Dear authors, I have read your paper "VoxAct-B: Voxel-Based Acting and Stabilizing Policy for Bimanual Manipulation" with great interest. The work presented is very impressive. I have a few questions regarding the training process: In your paper, it is mentioned that "We train the policy with a batch size of 1 on a single Nvidia 3000 series GPU for two days."
Thank you for your time and for sharing your research. Looking forward to your response. best