A method and device for training a convolutional neural network for image recognition

Abstract

The invention aims to provide a method and equipment for training a convolutional neural network used for image recognition. The method specifically comprises the steps of initializing a plurality of networks of the convolutional neural network on the same GPU (Graphics Processing Unit) according to parameter information of the convolutional neural network used for image recognition; distributing training image data corresponding to the convolutional neural network to the plurality of networks; carrying out parallel training processing on the plurality of networks according to the distributed training image data; and updating the parameter information of the convolutional neural network according to error information of the networks after training processing. Compared with the prior art, the same set of parameter information is utilized to initialize the plurality of networks of the convolutional neural network on the same GPU according to the method provided by the invention, the training image data is distributed to the plurality of networks so as to carry out parallel training processing, and the parameter information is updated by using the acquired error information, so that the single-card computational efficiency of the GPU is improved, waste of computing resources is reduced, and the recognition efficiency of the convolutional neural network for images is improved.

Description

Technical field [0001] This application relates to the computer field, and in particular to a technology for training a convolutional neural network for image recognition. Background technique [0002] With the rapid development of the Internet, the amount of image data in the network has surged, and the processing technology for image data has developed rapidly and is increasingly perfect. Among them, deep learning algorithms such as convolutional neural networks are widely used in image recognition and are reducing the complexity of network models. Significant results have been achieved in terms of improving the image data processing capabilities and other aspects. In order to improve the processing efficiency of data in image recognition, the current convolutional neural network based on GPU for image recognition learning and training mostly adopts a single-machine multi-GPU or multi-machine multi-GPU method. Among them, GPU (Graphics Processing Unit) is also called display co...

AI Technical Summary

Problems solved by technology

[0003] The purpose of this application is to provide a method and device for training convolutional neural networks used for image recognition to solve the problem of waste of resources caused by low efficiency of GPU-based convolutional neural network training for image recognition

[0004] According to one aspect of the present application, a method for training a convolutional neural network for image recognition is provided, which solves the problem of waste of resources caused by GPU-based training of a convolutional neural network for image recognition, Wherein the method includes:

Images