Network model quantification method, device, computer equipment and storage medium

Abstract

The invention discloses a network model quantification method, device, computer equipment, and storage medium, which are applicable to the technical field of artificial intelligence. The network model quantification method includes: acquiring a network model to be processed, and weight parameters of the network model to be processed according to the quantification requirement Quantize the activation output and the activation output respectively to obtain the initial weight parameter and the initial quantization parameter of the activation output, and construct the initial network model; obtain the first calibration network model, adjust the initial weight parameter of the initial network model based on the first calibration network model, and obtain The first preprocessing model: obtaining a second calibration network model, and adjusting the initial quantization parameters of the activation output of the first preprocessing model based on the second calibration network model to obtain a target network model. This method can solve the problem that the precision of the deep neural network model is reduced by reducing the size of the large deep neural network model by means of model compression such as quantization and cropping.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a network model quantification method, device, computer equipment and storage medium. Background technique [0002] With the continuous development of artificial intelligence technology, the application of artificial intelligence technology is becoming more and more extensive. In the field of artificial intelligence technology, deep learning is one of the more typical technologies. The essence of deep learning is an artificial neural network, and a neural network with many layers is called a deep neural network. At present, although the capabilities of deep neural network models in image classification and detection are close to or surpass those of humans, in actual deployment, there are still problems such as large models and high computational complexity, which require high hardware costs. In practical applications, in order to reduce hardware costs, neural netw...

AI Technical Summary

Problems solved by technology

[0005] In view of this, embodiments of the present invention provide a network model quantization method, device, computer equipment, and storage medium to solve the problem of shrinking large-scale deep neural network models through model compression such as quantization and cropping. The accuracy of deep neural network models is relatively low. low problem

Images