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

Abstract

The invention discloses a compression method and a compression device of a deep neural network model, a terminal and a storage medium. The method comprises the following steps: obtaining a trained deep neural network model; quantifying parameters of each layer in the deep neural network model layer by layer, performing iterative quantification N times for the deep neural network model, until realizing that the quantified deep neural network model satisfies preset compression volume requirements, wherein, quantification treatment is executed for the i layer parameters in the trained deep neuralnetwork model as follows: performing clustering analysis for the i layer parameters in the trained deep neural network model, and determining corresponding quantification range and quantification level according to a clustering analysis result; and quantifying the parameters in the quantification range of the i layer according to the determined quantification level. By the scheme above, precisionand validity of the deep neural network model can be considered while the deep neural network model is compressed.

Description

technical field [0001] The present invention relates to the technical field of information processing, and 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 research on deep neural network related technologies, a large number of deep neural network related technologies have emerged in related fields, such as convolutional neural networks applied in the field of vision and recurrent neural networks applied in speech recognition or natural language processing. etc., these neural network technologies have greatly improved the processing accuracy in the corresponding fields. [0003] Compared with shallow learning, deep neural networks have great potential for development. Through the multi-layer processing structure of the deep neural network model, the representative features of the samples can be extracted and analyzed, the sample features can be trans...

AI Technical Summary

Problems solved by technology

Although this can compress the neural network model to a certain extent, the accuracy and effectiveness of the compressed deep neural network model are low

Images