Zhejiang University

Hangzhou Hikvision Digital Technology Co., Ltd.

Huan Wang

Weimin Ma

Lei Zhang

Can You

Chenyi Shen

Haoji Hu

Ottoman

Armchair

The present invention provides an efficient image classification method based on structured pruning, which incorporates a spatial pruning method based on variation regularization, including steps such as image data preprocessing, inputting images to neural network, image model pruning and retraining, and new image class predication and classification. The present invention adopts a structured pruning method that removes unimportant weight parameters of the original network model and reduces unnecessary computational and memory consumptions caused by the network model in image classification to simplify the image classifier, and then uses the sparsified network model to predict and classify new images. The simplified method according to the present invention improves the original network model in image classification efficiency by nearly two times, costs about 30% less memory consumption and produces a better classification result.

Efficient image classification method based on structured pruning

Provided in an embodiment of the present application are an anti-shake method for a camera and a camera. The method comprises: obtaining current shake data of a camera, wherein the shake data comprises position change data of the camera when the camera shakes, and the shake data is detected by a shake detector; determining, according to a preset relationship between position change of an anti-shake lens for shake compensation and shake data, movement data of the anti-shake lens; and adjusting a position of the anti-shake lens according to the movement data, so that an image sensor captures a shake-compensated image. By applying the embodiment of the present application, anti-shake processing can be performed for the higher or lower frequency shake, improving anti-shake performance.

Anti-shake method for camera and camera

Growing community of inventors

Zhejiang, China

Huan Wang