Public Timelines

For educational institutions For teachers For students Cabinet

For educational institutions For teachers For students Open cabinet

Create a timeline

Public timelines

About & Feedback Accordo Privatezza FAQ

Cabinet Get premium

Donate

8 marzo 2019 anni - ChengGong: $\mu$L2Q: An Ultra-Low Loss Quantization Method for DNN

Descrizione:

本文实现了多位宽的量化方案。相比于二值三值或者定点数量化等方案，本文首次从权值分布角度进行量化，实现了多位宽的高精度量化。实验表明再相同条件下，uL2Q可以实现更低精度下降。

Aggiunto al nastro di tempo:

Quantization timeline

29 mar 2020

1

0

810

Data:

8 marzo 2019 anni

Adesso

~ 6 years and 7 months ago

About & Feedback Accordo Privatezza FAQ

Cabinet Get premium

Donate

The service accepts bank transfer (ACH, Wire) or cards (Visa, MasterCard, etc). Processed by Stripe.

Secured with SSL