Model Compression and Acceleration: Lip Recognition Based on Channel-Level Structured Pruning
In recent years, with the rapid development of deep learning, the requirements for the performance of the corresponding real-time recognition system are getting higher and higher. However, the rapid expansion of data volume means that time delay, power consumption, and cost have become problems that...
Main Authors: | Yuanyao Lu, Ran Ni, Jing Wen |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/20/10468 |
Similar Items
-
Optimization Based Layer-Wise Pruning Threshold Method for Accelerating Convolutional Neural Networks
by: Yunlong Ding, et al.
Published: (2023-07-01) -
Channel Pruning Method Based on Decoupling Feature Scale Distribution in Batch Normalization Layers
by: Zijie Qiu, et al.
Published: (2024-01-01) -
Channel Pruning of Transfer Learning Models Using Novel Techniques
by: Pragnesh Thaker, et al.
Published: (2024-01-01) -
Acceleration of LSTM With Structured Pruning Method on FPGA
by: Shaorun Wang, et al.
Published: (2019-01-01) -
PruneFaceDet: Pruning lightweight face detection network by sparsity training
by: Nanfei Jiang, et al.
Published: (2022-12-01)