alecwangcq / GraSP

Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH

alecwangcq/GraSP Issues

Test accuracy for tiny-imagenet
Updated 3 years ago
Question about the learning rate and weight decay in ResNet50 training on Imagenet
Closed 3 years ago1
Question: Why is are the inputs/targets split into different batches?
Closed 4 years ago1
Some questions about your paper and code
Closed 4 years ago9
Question about Hessian-gradient product
Closed 4 years ago
Question about score normalization
Closed 4 years ago1