Convolutional neural network compression method based on global feature relationship

Abstract

The invention belongs to the field of computer science, and discloses a convolutional neural network compression method based on a global feature relationship. According to the method, a global feature relationship (GFR) submodule is added behind a Batch Normalization (BN) layer of the convolutional neural network, so that the aims of extracting a channel relationship and suppressing an unimportant channel are fulfilled. The GFR sub-module mainly relates to pooling, full connection layer and moving average operation. Then, the importance degree of each channel is evaluated by combining the channel relationship and the channel scale factor of the BN layer, and the index can help the model compression method to screen out important channels in the model more accurately. And finally, by utilizing a channel pruning algorithm and a grid search technology, the compression of the network model is completed by consuming less time and computing resources without finely adjusting the model, so the running memory and the storage memory of the model are remarkably reduced, and the deduction speed of the model is increased, so the possibility of deploying the convolutional neural network on thesmall mobile device is greatly improved.

Description

technical field [0001] The invention belongs to the field of computer science and relates to the application of artificial intelligence technology, in particular to a convolutional neural network compression method based on global feature relationships. Background technique [0002] Thanks to the in-depth development of GPU and other computing platforms, deep learning was born and developed rapidly, which greatly narrowed the gap between science and practical application. The deep learning model represented by Convolutional Neural Network (CNN) has made amazing achievements in the fields of computer vision and natural language processing. Various vision tasks such as pattern recognition, image classification, object detection, etc. are well done. [0003] However, due to the complex model of the traditional convolutional neural network, the network model takes up a large amount of memory and the inference speed is slow; this seriously hinders the application of the convolut...

AI Technical Summary

Problems solved by technology

[0003] However, due to the complex model of the traditional convolutional neural network, the network model takes up a large amount of memory and the inference speed is slow; this seriously hinders the application of the convolutional neural network on mobile devices such as mobile phones and smart bracelets

And as the model becomes more complex, invalid neurons are more likely to appear in the network model

Images