class-incremental-learning
class-incremental-learning copied to clipboard
training hyperparamters for imagenet1000?
Hello, I would like to ask what is the hyperparameter setting of training Imagenet1000, is it the same as that of Imagenet100?
Thanks for your interest in our work!
We're using the same hyperparameters as the baselines:
- For LUCIR+AANets, you may see the hyperparameters here;
- For PODNet+AANets, you may see the hyperparameters here.
If you have any further questions, please do not hesitate to contact us.
Best,
Yaoyao
Thank you very much!