fsp_loss为program内的teacher var和student var添加fsp loss,出自论文 `A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning <http://openaccess.thecvf.com/content_cvpr_2017/papers/Yim_A_Gift_From_CVPR_2017_paper.pdf>`_
fsp_loss出自论文 `A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning <http://openaccess.thecvf.com/content_cvpr_2017/papers/Yim_A_Gift_From_CVPR_2017_paper.pdf>`_
为program内的teacher var和student var添加soft label loss
soft_label_loss为program内的teacher var和student var添加soft label loss,出自论文 `Distilling the Knowledge in a Neural Network <https://arxiv.org/pdf/1503.02531.pdf>`_
soft_label_loss出自论文 `Distilling the Knowledge in a Neural Network <https://arxiv.org/pdf/1503.02531.pdf>`_