THE EFFECT OF NEURAL NETWORK HYPERPARAMETERS ON THE QUALITY OF OBJECT RECOGNITION
Authors:
1.
Interspecific Center for Training and Combat Use of Electronic Warfare Troops (training and testing)
Russian Federation
Russian Federation
2.
Interspecific Center for Training and Combat Use of Electronic Warfare Troops (training and testing)
Russian Federation
Russian Federation
Type:
Сonference article
Published:
14.04.2025
Subject area:
004.8
Language:
Russian
Keywords:
neural network, convolutional neural network, yolov8
Abstract (English):
This article discusses the main stages of training a neural network model for determining objects in real time, as well as the influence of some hyperparameters on the accuracy and speed of the model being trained based on the YOLOv8 architecture.
This article discusses the main stages of training a neural network model for determining objects in real time, as well as the influence of some hyperparameters on the accuracy and speed of the model being trained based on the YOLOv8 architecture.
Keywords:
neural network, convolutional neural network, yolov8
neural network, convolutional neural network, yolov8
1. Komp'yuternoe zrenie. Sovremennye metody i perspektivy razvitiya / red. R. Devis, M. Terk; per. s angl. V. S. Yacenkova. – M.: DMK Press, 2022. – 690 s.: il.
2. Iskusstvennyy intellekt i komp'yuternoe zrenie. Real'nye proekty na Python, Keras i TensorFlow. — SPb.: Piter, 2023. — 624 s.: il. — (Seriya «Bestsellery O’Reilly»).
3. Osnovy iskusstvennogo intellekta v primerah na Python. Samouchitel'. — 2-e izd., pererab. i dop. — SPb.: BHV-Peterburg, 2024. — 448 s.: il. — (Samouchitel').
