About the dataset split of the grasp anything++ training and val.

Fsoft-AIC / LGD

Dataset and Code for CVPR 2024 paper "Language-driven Grasp Detection."

https://airvlab.github.io/grasp-anything/

MIT License

22 stars 2 forks source link

About the dataset split of the grasp anything++ training and val. #11

Open unira-zwj opened 6 days ago

unira-zwj commented 6 days ago

Glad you shared such a great job.

I noticed in the code that the number of split/grasp-anything++/train/seen.obj is 14516, the number of split/grasp-anything++/test/seen.obj is 573, and the number of split/grasp-anything++/test/unseen.obj is 230.

Is these number the correct setting?

andvg3 commented 22 hours ago

Hi @unira-zwj ,

To some extent, yes. I set the small number for testing. For more comprehensive results, you can increase the number of samples by appending seen.obj and unseen.obj with more idx of the samples.