Neural network quantization method, image recognition method, device and computer equipment

Abstract

The present application relates to a neural network quantization method, an image recognition method, a neural network quantization device, an image recognition device, computer equipment and a readable storage medium. The method includes: adjusting the network parameters and operation attribute parameters of the initial neural network based on the prediction loss and operation loss of the training samples to obtain the target operation attribute parameters after training; the operation attribute parameters represent the network layers in the neural network The value of the operation attribute, the operation amount loss is positively correlated with the actual operation amount associated with the operation attribute parameter; the neural network is quantified by using the target operation attribute parameter, and the quantized neural network is obtained. Adopting the method can avoid the problem that the prediction accuracy of the quantized neural network is seriously reduced, and realize reasonable quantification.

Description

technical field [0001] The present application relates to the technical field of neural networks, in particular to a neural network quantization method, an image recognition method, a neural network quantization device, an image recognition device, computer equipment and a readable storage medium. Background technique [0002] With the development of neural network technology, neural network quantization technology has emerged, mainly for model parameter values ​​and activation values ​​(output values ​​or input values) in each network layer (such as convolutional layer and fully connected layer) in the neural network. , input feature maps, etc. to compress, reduce the bit width of model parameter values, bit width of activation values, and the size (height and width) of input feature maps, etc., so as to realize the compression of the data volume of neural network model files and reduce the neural network model For purposes such as computing resource requirements during the...

AI Technical Summary

Problems solved by technology

[0004] However, although this neural network quantization technique can reduce the computational load of the neural network, it may lead to a serious reduction in the prediction accuracy of the quantized neural network, and there is a problem of unreasonable quantization.

Images