Class-balanced-loss-pytorch
Pytorch implementation of the paper Class-Balanced Loss Based on Effective Number of Samples presented at CVPR'19.
Yin Cui, Menglin Jia, Tsung-Yi Lin(Google Brain), Yang Song(Google), Serge Belongie
Dependencies
- Python (>=3.6)
- Pytorch (>=1.2.0)
Review article of the paper
How it works
It works on the principle of calculating effective number of samples for all classes which is defined as:
Thus, the loss function is defined as:
Visualisation for effective number of samples
