Network model fine adjustment method and system adapting to target data set, terminal and storage medium

Abstract

The invention provides a network model fine adjustment method and system adapting to a target data set, a terminal and a storage medium. The system comprises an original neural network, a target neural network, and a fine adjustment module. The original neural network comprises a unified neural network layer and an output layer, and the original neural network is used for pre-training the originalneural network by using an original data set to obtain parameters of each layer of the pre-trained original neural network and marking the parameters. The target neural network comprises network layers matched with those of the original neural network, the target neural network also comprises an output layer and a unified neural network layer, and the parameters of the unified neural network layer in the target neural network adopt the parameters of the unified neural network layer in the original neural network. The fine adjustment module is used for finely adjusting the characteristic parameters of all the layers except the output layer in the target neural network so as to adapt to a recognition target.

Description

technical field [0001] The invention relates to the technical field of automotive electronics, in particular to a fine-tuning method, system, terminal and storage medium for a network model adapting to a target data set. Background technique [0002] The three-dimensional parking garage is a mechanical or mechanical equipment system used to store and store vehicles in large quantities. For professional parking lot management companies, the three-dimensional garage is an effective means to increase the capacity of the parking lot and increase the income of parking fees. The three-dimensional parking garage is divided into two types: independent and built-in. The independent parking building is suitable for underground squares and existing buildings to supplement parking facilities. Planning and construction should pay attention to the surrounding environment. [0003] The built-in three-dimensional garage is suitable for simultaneous planning and construction of new building...

AI Technical Summary

Problems solved by technology

[0004] Autonomous valet parking (autonomous valet parking), as an important function of advanced assisted driving system, has basically been able to realize parking functions in parking lots, parks and other scenes, but there are still many limitations, such as the same parking space recognition network The model can only have obvious effects on the same type of training set, but the recognition effect on different types of parking spaces such as grass parking spaces, brick parking spaces, and three-dimensional parking spaces is poor

Images