Загрузка страницы

quarter CNN: Region Proposal Network (RPN)

The lecture introduces region proposal network (RPN) which is a convolutional neural network (CNN) for generating object proposals.
It was proposed in the paper entitled as "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Network”, NIPS, 2015.

The outline of this lecture includes:
(1) Introduction about what object detection is and the background of RPN.
(2) RPN architecture about the anchor for encoding object proposal, convolutional networks and contribution of RPN.
(3) RPN training about the training steps, the rules for anchor selection, and the loss function defined for training RPN

If you have any questions, a google meeting (https://meet.google.com/xya-vuys-vfo) is open for discussion at 10:00 PM ~ 10:30 PM (UTC+8) every Wednesday.

Any comments are welcome.

website: http://gg.gg/quarter
email: quarterhuang2018@gmail.com

Видео quarter CNN: Region Proposal Network (RPN) канала Shih-Shinh Huang
Показать
Комментарии отсутствуют
Введите заголовок:

Введите адрес ссылки:

Введите адрес видео с YouTube:

Зарегистрируйтесь или войдите с
Информация о видео
21 марта 2020 г. 9:16:17
00:19:09
Яндекс.Метрика