Machine learning: model compression techniques and deployment on Android platform
As Artificial Intelligence (AI) industry grows rapidly in recent years, many applications of deep learning are applied in mobile devices where resources are limited. Therefore, model compression and acceleration techniques are of great importance for achieving real-time requirements. In this study,...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156646 |
| _version_ | 1811687566486798336 |
|---|---|
| author | Jin, Chengkai |
| author2 | Jun Zhao |
| author_facet | Jun Zhao Jin, Chengkai |
| author_sort | Jin, Chengkai |
| collection | NTU |
| description | As Artificial Intelligence (AI) industry grows rapidly in recent years, many applications of deep learning are applied in mobile devices where resources are limited. Therefore, model compression and acceleration techniques are of great importance for achieving real-time requirements. In this study, several classic model compression techniques are discussed and compared by their performance on image recognition task. Additionally, an Android application able to classify images is built. |
| first_indexed | 2024-10-01T05:18:21Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/156646 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:18:21Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1566462022-04-22T00:03:56Z Machine learning: model compression techniques and deployment on Android platform Jin, Chengkai Jun Zhao School of Computer Science and Engineering junzhao@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision As Artificial Intelligence (AI) industry grows rapidly in recent years, many applications of deep learning are applied in mobile devices where resources are limited. Therefore, model compression and acceleration techniques are of great importance for achieving real-time requirements. In this study, several classic model compression techniques are discussed and compared by their performance on image recognition task. Additionally, an Android application able to classify images is built. Bachelor of Engineering (Computer Science) 2022-04-22T00:03:56Z 2022-04-22T00:03:56Z 2022 Final Year Project (FYP) Jin, C. (2022). Machine learning: model compression techniques and deployment on Android platform. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156646 https://hdl.handle.net/10356/156646 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Jin, Chengkai Machine learning: model compression techniques and deployment on Android platform |
| title | Machine learning: model compression techniques and deployment on Android platform |
| title_full | Machine learning: model compression techniques and deployment on Android platform |
| title_fullStr | Machine learning: model compression techniques and deployment on Android platform |
| title_full_unstemmed | Machine learning: model compression techniques and deployment on Android platform |
| title_short | Machine learning: model compression techniques and deployment on Android platform |
| title_sort | machine learning model compression techniques and deployment on android platform |
| topic | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | https://hdl.handle.net/10356/156646 |
| work_keys_str_mv | AT jinchengkai machinelearningmodelcompressiontechniquesanddeploymentonandroidplatform |