Deep Learning Models Compression for Agricultural Plants
Deep learning has been successfully showing promising results in plant disease detection, fruit counting, yield estimation, and gaining an increasing interest in agriculture. Deep learning models are generally based on several millions of parameters that generate exceptionally large weight matrices....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/19/6866 |
| _version_ | 1797552248352407552 |
|---|---|
| author | Arnauld Nzegha Fountsop Jean Louis Ebongue Kedieng Fendji Marcellin Atemkeng |
| author_facet | Arnauld Nzegha Fountsop Jean Louis Ebongue Kedieng Fendji Marcellin Atemkeng |
| author_sort | Arnauld Nzegha Fountsop |
| collection | DOAJ |
| description | Deep learning has been successfully showing promising results in plant disease detection, fruit counting, yield estimation, and gaining an increasing interest in agriculture. Deep learning models are generally based on several millions of parameters that generate exceptionally large weight matrices. The latter requires large memory and computational power for training, testing, and deploying. Unfortunately, these requirements make it difficult to deploy on low-cost devices with limited resources that are present at the fieldwork. In addition, the lack or the bad quality of connectivity in farms does not allow remote computation. An approach that has been used to save memory and speed up the processing is to compress the models. In this work, we tackle the challenges related to the resource limitation by compressing some state-of-the-art models very often used in image classification. For this we apply model pruning and quantization to LeNet5, VGG16, and AlexNet. Original and compressed models were applied to the benchmark of plant seedling classification (V2 Plant Seedlings Dataset) and Flavia database. Results reveal that it is possible to compress the size of these models by a factor of 38 and to reduce the FLOPs of VGG16 by a factor of 99 without considerable loss of accuracy. |
| first_indexed | 2024-03-10T15:57:17Z |
| format | Article |
| id | doaj.art-e046ca08dd354375846ee944a0fd155c |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T15:57:17Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e046ca08dd354375846ee944a0fd155c2023-11-20T15:35:51ZengMDPI AGApplied Sciences2076-34172020-09-011019686610.3390/app10196866Deep Learning Models Compression for Agricultural PlantsArnauld Nzegha Fountsop0Jean Louis Ebongue Kedieng Fendji1Marcellin Atemkeng2Department of Mathematics and Computer Science, Faculty of Science, University of Dschang, Dschang P.O. Box 96, CameroonDepartment of Computer Engineering, University Institute of Technology, University of Ngaoundere, Ngaoundere P.O. Box 454, CameroonDepartment of Mathematics, Rhodes University, Grahamstown 6140, South AfricaDeep learning has been successfully showing promising results in plant disease detection, fruit counting, yield estimation, and gaining an increasing interest in agriculture. Deep learning models are generally based on several millions of parameters that generate exceptionally large weight matrices. The latter requires large memory and computational power for training, testing, and deploying. Unfortunately, these requirements make it difficult to deploy on low-cost devices with limited resources that are present at the fieldwork. In addition, the lack or the bad quality of connectivity in farms does not allow remote computation. An approach that has been used to save memory and speed up the processing is to compress the models. In this work, we tackle the challenges related to the resource limitation by compressing some state-of-the-art models very often used in image classification. For this we apply model pruning and quantization to LeNet5, VGG16, and AlexNet. Original and compressed models were applied to the benchmark of plant seedling classification (V2 Plant Seedlings Dataset) and Flavia database. Results reveal that it is possible to compress the size of these models by a factor of 38 and to reduce the FLOPs of VGG16 by a factor of 99 without considerable loss of accuracy.https://www.mdpi.com/2076-3417/10/19/6866deep learning modelscompressionagriculturemodels pruningmodels quantization |
| spellingShingle | Arnauld Nzegha Fountsop Jean Louis Ebongue Kedieng Fendji Marcellin Atemkeng Deep Learning Models Compression for Agricultural Plants Applied Sciences deep learning models compression agriculture models pruning models quantization |
| title | Deep Learning Models Compression for Agricultural Plants |
| title_full | Deep Learning Models Compression for Agricultural Plants |
| title_fullStr | Deep Learning Models Compression for Agricultural Plants |
| title_full_unstemmed | Deep Learning Models Compression for Agricultural Plants |
| title_short | Deep Learning Models Compression for Agricultural Plants |
| title_sort | deep learning models compression for agricultural plants |
| topic | deep learning models compression agriculture models pruning models quantization |
| url | https://www.mdpi.com/2076-3417/10/19/6866 |
| work_keys_str_mv | AT arnauldnzeghafountsop deeplearningmodelscompressionforagriculturalplants AT jeanlouisebonguekediengfendji deeplearningmodelscompressionforagriculturalplants AT marcellinatemkeng deeplearningmodelscompressionforagriculturalplants |