Метод построения сверточной нейросетевой модели обнаружения объектов с применением технологии трансфертного обучения Т. К. Нгуен, В. И. Сырямкин, Ч. Т. Нгуен [и др.]
Material type: ArticleContent type: Текст Media type: электронный Other title: An approach to design a convolutional neural network model for object detection using transfer learning technology [Parallel title]Subject(s): глубокое обучение | нейросетевые модели | обнаружение объектов | трансфертное обучениеGenre/Form: статьи в сборниках Online resources: Click here to access online In: Инноватика-2021 : сборник материалов XVII Международной школы-конференции студентов, аспирантов и молодых ученых, 22-23 апреля 2021 г., г. Томск, Россия С. 126-128Abstract: The use of deep learning to identify objects in photos or videos has been proposed by many researchers. However, in a practical, when the dataset is small, and the computational hardware is not powerful, the accuracy of the results will be affected. This paper discusses the problem of transfer learning in building a CNN network for specified practical problems.Библиогр.: 4 назв.
The use of deep learning to identify objects in photos or videos has been proposed by many researchers. However, in a practical, when the dataset is small, and the computational hardware is not powerful, the accuracy of the results will be affected. This paper discusses the problem of transfer learning in building a CNN network for specified practical problems.
There are no comments on this title.