target assign cost too much，and gpu util is low, how to improve it ?

[chenrui17]

when i set batch_size = 15, class_num = 6，and there are batch_size*class_num(90) times target assign operation, code is here : https://github.com/poodarchu/Det3D/blob/master/det3d/core/anchor/target_assigner.py#L31,
and by profile the program, this part accounts for about ~30% of the train time. so how to improve it ?

[poodarchu]

you can move target assign step into model forward function, this can accelerate the speed by a large margin.
or you can wait for my new codebase release, which is 3x faster than this Det3D.