|
ИСТИНА |
Войти в систему Регистрация |
ФНКЦ РР |
||
PerforatedCNNs: Acceleration through Elimination of Redundant Convolutionsстатья
- Авторы: Michael Figurnov, Dmitry Vetrov, Pushmeet Kohli
- Сборник: ICLR 2016 : International Conference on Learning Representations
- Год издания: 2016
- Место издания: San Juan, Puerto Rico
- Первая страница: 1
- Последняя страница: 12
- Аннотация: We propose a novel approach to reduce the computational cost of evaluation of convolutional neural networks, a factor that has hindered their deployment in low- power devices such as mobile phones. Inspired by the loop perforation technique from source code optimization, we speed up the bottleneck convolutional layers by skipping their evaluation in some of the spatial positions. We propose and analyze several strategies of choosing these positions. We demonstrate that perforation can accelerate modern convolutional networks such as AlexNet and VGG-16 by a factor of 2 × - 4 × . Additionally, we show that perforation is complementary to the recently proposed acceleration method of Zhang et al. [28].
- Добавил в систему: Журавлев Юрий Иванович