Reproducibility on STB/any other specific dataset.

[ashar6194]

Hi @boukhayma,

I am trying to reproduce your results for the STB Dataset. The models provided on the github page, perform very poorly when used to infer even 2D coordinates on the STB Test Dataset. Do you have a separate trained model for STB which you could provide?

At present, I am extracting a hand image cropped (size =150% of the bounding box) from the STB dataset, and performing the exact same image transformations as provided in the github repository here.

Also, can you provide the exact ids of vertices you used from the Mano mesh to interpolate the palm coordinate for data consistency (Mentioned in Section 8 of the paper)?