Code for ICCV2019 "Symmetric Cross Entropy for Robust Learning with Noisy Labels" https://arxiv.org/abs/1908.06112
- Python 3.5.2
- Tensorflow 1.10.1
- Keras 2.2.2
Simply run the code by python3 train_models.py
It can config with dataset, model, epoch, batchsize, noise_rate, symmetric or asymmetric type noise
The reprocuded results by Hanxun Huang are slightly better for all methods. The code can be found here: https://github.com/HanxunHuangLemonBear/SCELoss-Reproduce