A construction method of a mobile terminal flower recognition model

Abstract

The invention provides a construction method of a mobile terminal flower recognition model. The construction method comprises the following steps of S10, creating a convolutional neural network modelof a floating point type trained by an ImageNet data set; S20, adding a quantization operation, i.e., after weight reading and activation output in an original floating point calculation model, inserting an analog quantization operation; S30, training the convolutional neural network model by using the flower data set until the model converges; S40, converting a floating point model into a 8-bit integer operation model, and obtaining a flower recognition model; and S50, compiling the flower recognition model into an APK installation package by using a Bazel construction tool. According to thepresent invention, the floating point operation convolutional neural network for mobile terminal flower recognition is converted into the efficient 8-bit integer operation convolutional neural network, so that the model size is reduced, the model prediction time is shortened, and the precision is reduced very low.

Description

Technical field [0001] The invention belongs to the technical field of deep learning, and specifically relates to a method for constructing a mobile terminal flower recognition model. Background technique [0002] Convolutional neural networks have demonstrated excellent performance in many application fields with their powerful feature representation capabilities, such as flower recognition in image classification. However, deep learning is not only a theoretical innovation, but more importantly, it is applied to engineering practice to apply efficient algorithms. With the development of the chip industry and hardware technology, convolutional neural networks have gradually been applied to mobile devices and embedded platforms, such as smart phones. However, the devices in these peripheral applications generally have relatively low computing power and are also limited by memory and power consumption. Therefore, it is very necessary to quantify and compress the model to make it...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to overcome the problem that the flower recognition algorithm model based on the convolutional neural network is relatively large and the prediction time is long in the prior art, and propose a method for constructing a mobile terminal flower recognition model

Images