richardaecn / class-balanced-loss

Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019
MIT License
602 stars 68 forks source link

mini-batch E_{n} doesn't work #9

Open Yuranus opened 5 years ago

Yuranus commented 5 years ago

In each batch, I firstly compute one independent E{n} for that batch, but it doesn't work at all; but according to your code, E{n} is global, there exists only one value for entire mini-batch GD optimization process, it works evidently. I want to know the reason?