eladhoffer/bigBatch
Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training of neural networks"
PythonMIT
Stargazers
- 821760408-sp@Facebook
- amdegroot@talc.ai
- asetsuna
- ccurroEstee Lauder, The Cooper Union
- chengchengowen
- CorcovadoMing
- dasguptarMicrosoft AI and Research
- esafakArchipelago AI
- fly51flyPRIS
- ggsonic
- gongbudaizhe
- gujiuxiangAdobe Research
- gurudave
- igorber
- JaredYeDHChina
- jdc08161063
- jfsantos@NVIDIA
- keskarnitish
- layumiUniversity of Macau
- lyuwenyuHarbin Institute of Technology
- power0341
- qiaohaijunBeijing,China
- qingswuCanada
- ResByteTricog Health
- RishiSankineni@phdata
- ruotianluoWaymo
- sanketlokeBlacksburg, Virginia
- soumithMeta
- souravsingh
- stekaiser
- stella-gaoAmazon
- tensortalkYou're on TensorTalk.com!
- tsrxq
- xhwang
- yashk2810@google
- yupbank@Shopify