Accelerating automatic model finding with layer replications case study of MobileNetV2.

In this paper, we propose a method to reduce the model architecture searching time. We consider MobileNetV2 for 3D face recognition tasks as a case study and introducing the layer replication to enhance accuracy. For a given network, various layers can be replicated, and effective replication can yi...

Full description

Saved in:
Bibliographic Details
Main Authors: Kritpawit Soongswang, Chantana Chantrapornchai
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2024-01-01
Series:PLoS ONE
Online Access:https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0308852&type=printable
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849236563369656320
author Kritpawit Soongswang
Chantana Chantrapornchai
author_facet Kritpawit Soongswang
Chantana Chantrapornchai
author_sort Kritpawit Soongswang
collection DOAJ
description In this paper, we propose a method to reduce the model architecture searching time. We consider MobileNetV2 for 3D face recognition tasks as a case study and introducing the layer replication to enhance accuracy. For a given network, various layers can be replicated, and effective replication can yield better accuracy. Our proposed algorithm identifies the optimal layer replication configuration for the model. We considered two acceleration methods: distributed data-parallel training and concurrent model training. Our experiments demonstrate the effectiveness of the automatic model finding process for layer replication, using both distributed data-parallel and concurrent training under different conditions. The accuracy of our model improved by up to 6% compared to the previous work on 3D MobileNetV2, and by 8% compared to the vanilla MobileNetV2. Training models with distributed data-parallel across four GPUs reduced model training time by up to 75% compared to traditional training on a single GPU. Additionally, the automatic model finding process with concurrent training was 1,932 minutes faster than the distributed training approach in finding an optimal solution.
format Article
id doaj-art-c0dc3da2553340c8a12765189488dde0
institution Kabale University
issn 1932-6203
language English
publishDate 2024-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-c0dc3da2553340c8a12765189488dde02025-08-20T04:02:13ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-01198e030885210.1371/journal.pone.0308852Accelerating automatic model finding with layer replications case study of MobileNetV2.Kritpawit SoongswangChantana ChantrapornchaiIn this paper, we propose a method to reduce the model architecture searching time. We consider MobileNetV2 for 3D face recognition tasks as a case study and introducing the layer replication to enhance accuracy. For a given network, various layers can be replicated, and effective replication can yield better accuracy. Our proposed algorithm identifies the optimal layer replication configuration for the model. We considered two acceleration methods: distributed data-parallel training and concurrent model training. Our experiments demonstrate the effectiveness of the automatic model finding process for layer replication, using both distributed data-parallel and concurrent training under different conditions. The accuracy of our model improved by up to 6% compared to the previous work on 3D MobileNetV2, and by 8% compared to the vanilla MobileNetV2. Training models with distributed data-parallel across four GPUs reduced model training time by up to 75% compared to traditional training on a single GPU. Additionally, the automatic model finding process with concurrent training was 1,932 minutes faster than the distributed training approach in finding an optimal solution.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0308852&type=printable
spellingShingle Kritpawit Soongswang
Chantana Chantrapornchai
Accelerating automatic model finding with layer replications case study of MobileNetV2.
PLoS ONE
title Accelerating automatic model finding with layer replications case study of MobileNetV2.
title_full Accelerating automatic model finding with layer replications case study of MobileNetV2.
title_fullStr Accelerating automatic model finding with layer replications case study of MobileNetV2.
title_full_unstemmed Accelerating automatic model finding with layer replications case study of MobileNetV2.
title_short Accelerating automatic model finding with layer replications case study of MobileNetV2.
title_sort accelerating automatic model finding with layer replications case study of mobilenetv2
url https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0308852&type=printable
work_keys_str_mv AT kritpawitsoongswang acceleratingautomaticmodelfindingwithlayerreplicationscasestudyofmobilenetv2
AT chantanachantrapornchai acceleratingautomaticmodelfindingwithlayerreplicationscasestudyofmobilenetv2