Network model publishing method and device, computer equipment and storage medium

Abstract

The invention provides a network model publishing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring first image annotation data, wherein the image annotation data comprises element categories of multiple frames of images; screening a first target element category meeting a model release condition from the element categories of the multiple frames of images; obtaining a target image corresponding to the first target element category; splitting the target image into a current training image and a current prediction image in proportion; determining a to-be-trained network model, and training the to-be-trained network model through the current training image to obtain a trained detection model; predicting the detection model throughthe current prediction image to obtain a prediction reference value; and determining the release of the detection model according to the prediction reference value. Through the method, the model publishing efficiency can be improved.

Description

Technical field [0001] This application relates to the field of artificial intelligence technology, in particular to a network model publishing method, device, computer equipment and storage medium. Background technique [0002] With the development of science and technology, artificial intelligence technology has been widely used, for example, it has played a huge role in promoting service robots, intelligent terminals, search, big data, information classification and other fields. [0003] At present, most platforms have launched recommendation and search services based on artificial intelligence network models, but such recommendation and search services usually require an artificial intelligence network model to be built into the platform. These models require algorithm experts to obtain training data from the business side for training, and return the trained model to the business side for testing. Repeat the above steps until the test passes, and publish the final trained mod...

AI Technical Summary

Problems solved by technology

[0004] However, the current network model requires the participation of algorithm experts in the whole process from training to release, and requires repeated communication and confirmation between algorithm experts and the business side, resulting in a long cycle and high cost for model release

Images