How the "type_weight_list" is designed

[Betty-J]

Hi, thanks for sharing! I am trying to train Painter using toy_dataset. I found in /Painter/data/pairdataset.py that the data processing section is designed with a weight parameter called type_weight_list. In the original code, type_weight_list is defined as [0.1, 0.2, 0.15, 0.25, 0.2, 0.15, 0.05, 0.05]. May I ask what factors were considered for this design and how one should determine a new type_weight_list when working with other datasets?
Looking forward to your reply.