Neural network model processing method and device, electronic device and storage medium

Abstract

The invention discloses a neural network model processing method and device, and an electronic device. The method comprises the steps of obtaining a first neural network model; acquiring a first sample image, wherein the acquisition visual angle of the first sample image is a first visual angle; and based on the first sample image, training the first neural network model to obtain a trained firstneural network model.

Description

technical field [0001] The present application relates to computer vision technology, and in particular to a neural network model processing method and device, electronic equipment, and storage media. Background technique [0002] In recent years, computer vision technology has developed rapidly, and now people can use trained neural network models to complete various vision tasks, such as image classification, object tracking, face recognition, etc. [0003] Depending on the development of technology, the cost of training and using these neural network models is getting lower and lower. Platforms that support deep learning frameworks and some special hardware can load and use such neural network models, such as robots. The robot can be equipped with a visual sensor to obtain visual signal input and supports a deep learning framework. However, the viewing angle of the robot is looking up, so that the input of the sensor is limited by the viewing angle, and the neural networ...

AI Technical Summary

Problems solved by technology

However, the perspective of the robot is looking up, so the input of the sensor is limited by the perspective, and the neural network model cannot be directly transferred to the robot.

Images