about the camera params regression

[lvZic]

I found the cam params converge worse, and i use weak perspective in my code, in which kpy_2d = scale(kyp3d[, :2] + txy ). I think the key reason is the focal length of the dataset is different with each image, and it range from 400 mm to 800 mm. So maybe the network cannot regress the scale well?
As "It is common to assume a fixed focal length to perform perspective projection. " . I wonder if the performance would be improved if i use perspective projection instead of weak perspective?