Modularization of files and nice details implemented

varungohil / Generalizing-Lottery-Tickets

This repository contains code to replicate the experiments given in NeurIPS 2019 paper "One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers"

https://rescience.github.io/bibliography/Gohil_2020.html

MIT License

51 stars 9 forks source link

Modularization of files and nice details implemented #4

Closed fcorencoret closed 4 years ago

fcorencoret commented 4 years ago

Separated files within their scope (utils, dataloaders, models, parsers) and implemented nice training details as:

tqdm progress bar for each pruning_iter - showing the accuracy of the last epoch during that iteration
DataParallel to train models several GPUs

sdeepaknarayanan commented 4 years ago

Hi @fcorencoret, thank you for your interest in our repository.

We are currently busy but hope to get back to this PR ASAP.

sdeepaknarayanan commented 4 years ago

Hi @fcorencoret , we will merge your PR to a new branch dev. We would like to keep master intact for now.