Nicolas Playe

Moreover, I think for better warmup convergence, using early stopping could increase your results. As I see you have fixed a variable to set the number of warmup_step. It could...

Another thing, I think that using the confidence entropy to get the prediction confidence (relative percentage from threshold ) could be better to evaluate if the data is in the...

Another tip, as I see your concurrents used larger models, maybe doing like them should improve results.. I have a question: when you talk about cifar10-sym90, you say that 10%...

I would try another thing not use the same model twice in the iteration but two different architectures. And waiting in warmup step that the 2 models converge independently

Another thing (sorry for disturbing); it it better to quantify the overall probability of confidence over all the class than just using best prediciton for prob_his1 and prob_his2 like ```...

For args.md maybe trying: - a linear scheduler that converge linearly from 0 to 1 - using a metric like accuracy on val (if 96% of accuracy) to fix m...

on the lines pred1 = prob1 > 0.5 pred2 = prob2 > 0.5 I think determining the best threshold that maximize f1_score or precision or recall (you have the choice)...

It should be better to not use this on hyperparmeter ``` lr = args.learning_rate if epoch >= args.lr_switch_epoch: lr /= 10 ``` but more a LrScheduler like these: [lr_scheduler.LinearLR](https://pytorch.org/docs/stable/generated/torch.optim.lr_scheduler.LinearLR.html#torch.optim.lr_scheduler.LinearLR) It...

In definitive , the less hyperparameters you will have, the more stable your results will be. If you want some help in the next months, I can make a state...