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

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