Training method and apparatus of neural network, and object identification method and apparatus

Abstract

The embodiment of the invention discloses a training method and apparatus of a neural network, and an object identification method and apparatus. The training method of a neural network includes the steps: establishing an initial neural network model, wherein the initial neural network model, is an ultra lightweight network SqueezeNet model; acquiring a training sample, and preprocessing the training sample; inputting the training sample which is obtained through preprocessing into the initial neural network model, and according to the first output of determining the loss value of the first output and the preset expectation according to the initial neural network model; and according to the loss value, adjusting the network parameters of the initial neural network model, and generating a target neural network model. The training method of a neural network establishes a high precision target neural network with few parameters and small occupied memory, so as to enable the target neuralnetwork model which is obtained through training to be applied to a mobile terminal, without depending on setting of a GPU (Graphics Processing Unit), thus improving adaptability of the target neuralnetwork model.

Description

technical field [0001] Embodiments of the present invention relate to image processing technology, and in particular to a neural network training method, object recognition method and device. Background technique [0002] With the rapid development of deep learning technology, deep convolutional neural networks have achieved major technological breakthroughs and rapid development in the fields of object recognition, single object positioning, multi-object detection, and image semantics and instance segmentation. In the top international large-scale object recognition competition, the recognition accuracy of object recognition technology based on deep convolutional neural network has reached a recognition rate that surpasses that of humans. [0003] However, the current neural network model needs to use a corresponding computing framework. By arranging multiple high-performance graphics processors (GPU, Graphics Processing Unit), and occupying a large amount of memory, it can...

AI Technical Summary

Problems solved by technology

[0003] However, the current neural network model needs to use a corresponding computing framework. By arranging multiple high-performance graphics processors (GPU, Graphics Processing Unit), and occupying a large amount of memory, it cannot be applied to a traditional central processing unit with a small memory space. Mobile terminals such as smartphones or tablets

Images