what scale signifies in get_affine_transform function?

[fused-byte]

Hey, first of all, thanks for making the code available.

I am having a hard time understanding the calculation done on the variable 'scale' at different places. I am implementing the pose estimation of something other than human. Do I still have to use the pixel_std=200? What would happen if my object is smaller than 200px?

What is the purpose of the "get_affine_transform" function? from visualization, I can see that it aligns the center of the object with the image. but its dependency on 'scale' is something I am not able to understand. I would appreciate the help here.