About the precomputed Grasp Points datasets

[YongLD]

I would like to detect the best Grasp point in YCB_Video datasets, but I don't know how to create the Grasp point detection datasets. I find you have made the precomputed Grasp Points datasets. Could you tell me how to create the precomputed points? If possible, Could you provide the datasets for me? Thanks for your assistance.

[gidobot]

We did not generate a full grasp point dataset for YCB_Video, as this was not the main focus for SilhoNet. I would suggest looking into something like DexNet for generating grasp points.