add the config of orientation model
add the preprocess op RandomRot90 that can rotate the img and return the orientation
add the CustomLabelDataset that support getting label by preprocess
refactor some preprocess ops to support dict parameter and return dict

* add weighted soft labels loss function

add weighted soft labels loss function

* fix typo in docs/zh_CN/advanced_tutorials/knowledge_distillation.md

the error would be raised when when the pattern string represents nested, e.g., containing "[3][1]".