30
/ru/
AIzaSyAYiBZKx7MnpbEhh9jyipgxe19OcubqV5w
April 1, 2024
3255110
288434
1
Public Timelines FAQ
Public TimelinesFAQ
Public TimelinesFAQ
For educational institutions For teachers For students Open cabinet
For educational institutions For teachers For students Open cabinet
Создать
Create a timeline
Public timelines
Library
FAQ

2 янв 2018 г. - Deep Neural Network Compression with Single and Multiple Level Quantization

Описание:

本文首次同时在宽度和深度上进行量化，SLQ/MLQ。首先在宽度上，使用SLQ，将权值划分为量化部分和重训练部分，通过重训练部分降低量化损失。在深度上，使用MLQ，通过将损失累计到下一层迭代，以降低当前层的量化损失。

Добавлено на ленту времени:

Quantization timeline

By龚成
29 мар 2020

Дата:

2 янв 2018 г.
Сейчас
~ 6 гг и 4 мес назад
About & FeedbackСоглашениеПриватностьБиблиотека
2024 © Time.Graphics
Support 24/7  
CabinetGet premium
Donate
The service accepts bank transfer (ACH, Wire) or cards (Visa, MasterCard, etc). Processed by Stripe.
Secured with SSL
Excellent (Trustpilot Reviews)
Based on 115+ reviews
Write your own review on Trustpilot.com