Shiyang Cheng

Thanks for the quick response! May I know if this is on your plan? If not, I will probably go into the codes sometime next week. Please do not close...

No problem as long as I could get some help from you. Regarding the gradient calculation, are you going to fix that problem soon? PS: I am still not sure...

Hello, this is caused by a bug in the code, when it loops through the data, the last batch does not always has the same number as the batch size....