What's the weights in the line 325 of class-balanced-loss/src/cifar_main.py

richardaecn / class-balanced-loss

Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

MIT License

597 stars 68 forks source link

Closed Bonsen closed 4 years ago

Bonsen commented 4 years ago

I should compute weights_per_cls of whole dataset or compute weights_per_cls of each batch ? There may be 0 in weights_per_cls of each batch.