How to speed up the loss computation in DTSH

[ssqiao]

Hi, swuxyj. Nice work for this community.
It is noted that the training loss of DTSH contains a for loop which is somewhat time-consuming. Is there any change to speed up this op? It seems that the for loop can be parallelized.

[swuxyj]

Hi, swuxyj. Nice work for this community. It is noted that the training loss of DTSH contains a for loop which is somewhat time-consuming. Is there any change to speed up this op? It seems that the for loop can be parallelized.

可以参考其他人的实现，目前这个版本已经是我能想到的最优的方式了