Add Loss, Top1 and Top5 to iteration hook

MadryLab / robustness

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

MIT License

903 stars 181 forks source link

Open alexriedel1 opened 2 years ago

alexriedel1 commented 2 years ago

Hey, for improved custom logging, I think adding loss values to the iteration hook makes sense.