Claim · model-written summary
Improved YOLOv5s reduced floating point operations per second (FLOPs) by 48.7%.
- Taxon
- Rice
Oryza sativat0 - Outcome
- floating point operations per second (FLOPs)e0
- Direction
- reducede0
- Value
- 48.7%e0
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentComparatorSettingQualifier
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“Rice”
e0“It also reduced network parameters, model size, and the floating point operations per second (FLOPs) by 47.5, 45.7, and 48.7%, respectively.”
Title
Deep-Learning-Based Rice Disease and Insect Pest Detection on a Mobile Phone
Jizhong Deng; Chang Yang; Kanghua Huang; et al. Agronomy 2023. doi:10.3390/agronomy13082139
Other claims from this paper (14)
- Method / resource Improved YOLOv5s reached 0.931 F1-Score.
- Method / resource Improved YOLOv5s reached 0.961 mean average precision (mAP) (0.5).
- Method / resource Improved YOLOv5s reached 0.648 mAP (0.5:0.9).
- Method / resource Improved YOLOv5s reduced network parameters by 47.5.
- Method / resource Improved YOLOv5s reduced model size by 45.7.
- Method / resource Improved YOLOv5s increased inference speed by 38.6% versus original YOLOv5s.
- Method / resource Improved YOLOv7-tiny outperformed its original version in detection accuracy but ranked below Improved YOLOv5s.
- Method / resource Improved YOLOv5s performed better on large rice disease and pest targets.
- Method / resource Improved YOLOv7-tiny was more accurate on small targets.
- Method / resource On mobile FP16, Improved YOLOv5s achieved 0.925 precision.
- Method / resource On mobile FP16, Improved YOLOv5s achieved 0.939 recall.
- Method / resource On mobile FP16, Improved YOLOv5s achieved 374 ms/frame inference speed.
- Method / resource Both improved models accurately identified rice diseases and insect pests.
- Method / resource The mobile application provided a reference for fast field diagnosis.