Target detection model training method and device, electronic equipment and storage medium

Abstract

The invention discloses a target detection model training method and device, electronic equipment and a storage medium, and relates to the technical field of deep learning and computer vision. The specific implementation scheme is as follows: firstly, acquiring a plurality of sample sets of a plurality of targets in a preset scene; determining the sample sampling number of a single target in batchtraining according to the plurality of sample sets of the plurality of targets; then, in each batch of training, performing sampling from the sample set of each target according to the sample sampling number, and forming batch training data; and training the target detection model by using the batch training data until the training of the target detection model is completed. According to the method, when the training data is sampled, each target is sampled according to the sample sampling number, and the training data with the same number or approximately the same number can be obtained for training, so that the detection efficiency and the detection accuracy of the trained target detection model on each target are ensured.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, specifically to the technical field of deep learning and computer vision, and in particular to a training method, device, electronic equipment and computer-readable storage medium of a target detection model. Background technique [0002] With the development of deep learning, the target detection technology in computer vision has broad landing scenarios and feasibility. [0003] In order to make the target detection model achieve a good detection effect in a certain actual scene, in related technologies, a large amount of data is labeled for each recognized target, and a large amount of labeled training data is used to train the target detection model. However, in real-world scenarios, due to the different distribution of different categories of scenes, the number of training data for different targets in different categories of scenes is different and the distribution ...

AI Technical Summary

Problems solved by technology

However, in real-world scenarios, due to the different distribution of different categories of scenes, the number of training data for different targets in different categories of scenes is different and the distribution is not balanced. For example, the training data of the first target is very small, and the training data of the second target There is a lot of data, the training data of the second target is easy to be sampled, but the training data of the first target is not easy to be sampled, resulting in poor detection efficiency and low accuracy of the trained target detection model for the first target

Images