Error: Divided by 0.

[woriazzc]

Thanks for your the implementation!

In LsqQuan. https://github.com/zhutmost/lsq-net/blob/2c24a96be06d044fa4c7d651727f4574b8d88c86/quan/quantizer/lsq.py#L54 If s_scale contains 0, there will be Divided by 0 Error, and the training loss will become nan. Maybe eps should be used.

[zhutmost]

Looks that it is very rarely seen. s_scale is a floating pointed number, it generally does not become 0 during training.

I will try to add an eps, when I have spare time. (it need some experiments)

[lippman1125]

Looks that it is very rarely seen. s_scale is a floating pointed number, it generally does not become 0 during training. I will try to add an eps, when I have spare time. (it need some experiments)

Not rarely.

[flymmmfly]

Not rarely.