Compression method and device of deep neural network model, storage medium and terminal

Abstract

The invention discloses a compression method and device of a deep neural network model, a terminal and a storage medium. The method comprises the following steps: acquiring a trained deep neural network model; traversing all layers of a deep neural network to obtain parameters of a current traversed layer; and quantifying the parameters of the current traversed layer based on the density and extension range of the parameters until all the layers of the deep neural network are traversed to obtain a quantified deep neural network model. Through the scheme, the accuracy and validity of the deep neural network model can be improved during compression of the deep neural network model.

Description

technical field [0001] The invention relates to information processing technology, in particular to a compression method and device, a terminal, and a storage medium of a deep neural network model. Background technique [0002] With the rapid development of deep neural network-related technology research, a large number of deep neural network-related technologies have emerged in related fields, such as convolutional neural networks in the field of vision and recurrent neural networks in the field of speech recognition or natural language processing. etc. These neural network technologies have greatly improved the processing accuracy in the corresponding fields. [0003] Deep Neural Network Compared with shallow learning, deep neural network has great development potential. Through the multi-layer processing structure of the deep neural network model, the characteristic features of the sample can be extracted and analyzed, and the sample features can be transformed and calcu...

AI Technical Summary

Problems solved by technology

However, the compressed deep neural network model has the problem of low accuracy and effectiveness

Images