How could I get the center and scale of wild images?

[Zzlongjuanfeng]

In the WLFW model, the decoding of preds needs the center and scale to get final results. How could I get the center and scale of wild images (e.g. a cropped and resized face image)?

[lucaskyle]

the hrnet input size will be (256,256,3)

as far as i know : center=torch.tensor([[128.0,128.0]]) scale= torch.tensor([1.28])

so feed the network with 256*256 face image and u may get (a,98,2) results.

[starhiking]

#3