Model construction method and device, image processing method and device, hardware platform and storage medium

Abstract

The application relates to the technical field of deep learning, and provides a model construction method and device, an image processing method and device, a hardware platform and a storage medium. The model construction method comprises the steps that a neural network model used for image processing is trained, wherein the neural network model comprises at least one depth separable convolution module, and each depth separable convolution module comprises a layer-by-layer convolution layer, a point-by-point convolution layer, a batch normalization layer and an activation layer which are connected in sequence; and the trained neural network model is quantized to obtain a quantized neural network model. According to the method, firstly, model parameters are quantified, so that the data volume of the parameters is effectively reduced, and the model is suitable for being deployed in NPU equipment. Secondly, the depth separable convolution module in the method is different from the depth separable convolution module in the prior art, and a batch normalization layer and an activation layer are not arranged between a layer-by-layer convolution layer and a point-by-point convolution layer, so that values of model parameters are distributed in a reasonable range, and the model parameters can be quantized with high precision.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular, to a model building and image processing method, device, hardware platform and storage medium. Background technique [0002] Image processing technology is widely used in many fields, including face recognition and intelligent video analysis in the security field, traffic scene recognition in the traffic field, content-based image retrieval and automatic album classification in the Internet field, image recognition in the medical field, etc. In recent years, the industry has generally adopted neural network models to perform image processing tasks in specific fields, and achieved good results. [0003] Since the neural network model involves a large number of calculations, in the prior art, a Graphics Processing Unit (GPU) is generally used to accelerate calculations. However, the GPU has a large volume and relatively high power consumption. Unable to install. At pr...

AI Technical Summary

Problems solved by technology

However, the existing neural network is still designed for the GPU environment, and directly migrated to the NPU environment for use, the effect is not good

Images