the argument may be "infer_add_softmax" used in exporting.

Put the calling of update_res(), stop_after(), freeze_befor() to the construction method of the parent class. And the init_net() support to call stop_after() by config of Arch.

freeze subnet specified with the specified layer name by setting OutputTensor.stop_gradient=True

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