Home page

Deconstructing Deep Learning + δeviations

Drop me an email | RSS feed link : Click
Format : Date | Title
  TL; DR

Total number of posts : 89

Go To : PAPERS o ARTICLES o BOOKS o SPACE

View My GitHub Profile


Go to index

Bag Of Tricks

Reading time : ~5 mins

by Subhaditya Mukherjee

Paper notes for the paper

[24] Bag Of Tricks

Training procedure

Large batch training

Zero gamma

No bias decay

FP16

XResnet

One cycle

Label Smoothing CE

Distillation

Use mixup

Related posts:  FP16  AI Superpowers Kai Fu Lee  Digital Minimalism Cal Newport  More Deep Learning, Less Crying - A guide  Super resolution  Federated Learning  Taking Batchnorm For Granted  A murder mystery and Adversarial attack  Thank you and a rain check  Pruning