Data processing method, system and device and readable storage medium

Abstract

The invention discloses a data processing method. The method comprises the steps of marking each layer of a network model as a key layer or a non-key layer according to acquired structure informationof the network model; respectively determining a quantization bit width range of the key layer and a quantization bit width range of the non-key layer according to hardware resource information needing to be deployed; determining the optimal quantization bit width of each layer of the network model in the quantization bit width range; and training the network model based on the optimal quantization bit width of each layer of the network model to obtain an optimal network model, and performing data processing by using the optimal network model. According to the optimal network model obtained based on optimal quantization bit width training, the model structure is compressed to the maximum extent under the condition that the optimal precision of the network model is guaranteed, optimal deployment of a hardware end is achieved, and then the efficiency of processing data through the optimal network model is improved. The invention also provides a data processing system and device, and a readable storage medium, which have the above beneficial effects.

Description

technical field [0001] The present application relates to the field of data processing, in particular to a data processing method, system, device and readable storage medium. Background technique [0002] With the continuous development of artificial intelligence technology, artificial intelligence technology has gradually been applied in daily life. In the field of artificial intelligence technology, deep learning is one of the more typical technologies. Although the capabilities of deep neural networks 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, many neural networks are deployed on some terminal devices or edge devices. These devices generally have low computing power, and memory and power consumption are also limited. [0003] Therefore, i...

AI Technical Summary

Problems solved by technology

Regardless of the quantization model, researchers pre-set the quantization bit width based on prior knowledge before performing quantization processing, and seldom consider the actual model structure of the network and the hardware environment that needs to be deployed, resulting in the preset quantization bit width. It is suitable for the quantification of the network model structure, and cannot be optimally deployed in the corresponding hardware environment, resulting in low efficiency when using the network model to process data

Images