Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 2. Отображено 2.
26-05-2023 дата публикации

Deep convolutional neural network quantization pruning joint optimization method and system

Номер: CN116167413A
Автор: XU MINGKAI, REN ZHIGANG, LI CONG, YANG JIE, CHEN XIANDA, WANG SHUYING, WANG SIYUAN, LIU ZHAO, LIU XIAO, LIU YINAN, HU QINGHAO, GAO XIANG, SHAO SHUAI, ZHENG YIBIN, ZHANG YUWEI
Принадлежит:

The invention discloses a deep convolutional neural network quantization pruning joint optimization method and system, and belongs to the technical field of image processing, and the method comprises the steps: obtaining a data set of a to-be-processed object image; training a to-be-optimized neural network model by using the data set, and initializing neural network model parameters including an evaluation network parameter, an execution network parameter, a target evaluation network parameter and a target execution network parameter; obtaining an optimal weight pruning rate, a weight quantization rate and an input feature quantization rate of the neural network model by using a quantitative pruning strategy learning method based on reinforcement learning; retraining the neural network by using a post-training method based on distillation and quantization entropy regularization to obtain optimized neural network model parameters; and optimizing the neural network model by using the optimal ...

Подробнее
Номер записи: 1
11-08-2023 дата публикации

Water purification mechanism of water supply tank

Номер: CN116570991A
Автор: QI YULEI, XIN CHONGFA, GUO FENGLEI, LI PENG, CHEN JINJIANG, LIU YINAN
Принадлежит:

The invention relates to the technical field of secondary water supply, in particular to a water purification mechanism of a water supply tank, which comprises a tank body, a mounting cover is fixedly arranged on the outer wall of the top of the tank body in a penetrating manner, a driving part is arranged in the mounting cover, a rotating part is rotatably arranged in the tank body, and the driving end of the driving part is connected with the rotating part; a circular groove is formed in the outer wall of the rotating part, mounting grooves which are annularly distributed at equal intervals are formed in the inner wall of the circular groove, purification assemblies are arranged in the mounting grooves, a water discharging opening communicating with the mounting grooves is formed in the outer wall of the bottom of the rotating part, and a collecting box is fixedly arranged on the outer wall of one side of the box body. An impurity removing box is fixedly arranged on the outer wall of ...

Подробнее
Номер записи: 2