Efficient Execution via Dynamic Network Slimming
碩士 === 國立交通大學 === 電子研究所 === 108 === Convolutional neural networks (CNN) reach the state-of-the-art in computer vision. However, its huge computation and large model size cause that it is hard to execute on mobile and wearable devices with limited resources. Therefore, the model compression method an...
Main Authors: | Tseng, Yu-Che, 曾于哲 |
---|---|
Other Authors: | Chang, Tian-Sheuan |
Format: | Others |
Language: | en_US |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/m38494 |
Similar Items
-
Design and Implementation of a Sensorless Drive System for Slim Motors
by: Ren-Jhih Tseng, et al.
Published: (2007) -
Improving Network Slimming With Nonconvex Regularization
by: Kevin Bui, et al.
Published: (2021-01-01) -
Slim and Efficient Neural Network Design for Resource-Constrained SAR Target Recognition
by: Hongyi Chen, et al.
Published: (2018-10-01) -
Demonstration of the Novel Ultra-Slim Flexible Glass as Substrate with Metal Meshed Antenna
by: Chia-Ying Tseng, et al.
Published: (2016) -
The portability of BCPL to the MC68000 via the intermediate language SLIM
by: Ranger, Eric Alfrey
Published: (2010)