If I follow the default setting and run python main/train.py --cfg configs/cifar10.yaml, I cannot achieve similar results as reported in your paper.At the beginning, the loss of training set decreases, and the accuracy of verification set increases. However, after running for a period of time, the loss of training set will increase, and the accuracy of verification set will decrease, and fluctuate greatly. What's the matter?

megvii-research / BBN

The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

https://arxiv.org/abs/1912.02413

MIT License

657 stars 100 forks source link

Open ghost opened 3 years ago

ghost commented 3 years ago

If I apply it to my own dataset, the above problems will occur.

liangzz1991 commented 3 years ago

same question......and find this phenomenon occurs in half of the total epoch.....

costantine20 commented 3 years ago

do you solve the problem？

sunjiaqi401 commented 3 years ago

I also have this problem. For a long time, the accuracy of the test set does not rise, and then after such a period of time, it begins to rise again