A deep learning sample enhancement system and its operation method

Abstract

The invention discloses a deep learning sample enhancement system, comprising: a video module for recording and providing a video sequence, a detector for obtaining an optimized SSD network from the video sequence, a sample module including original samples of marked data, and a video sequence A sampling module, a screening module, and a labeling module for sampling detection and performing statistical analysis; meanwhile, the invention also discloses an operation method of a deep learning sample enhancement system. Through the deep learning sample enhancement system, the training samples are automatically selected, the diversity and complexity of the training samples are enhanced, the redundancy of the training samples is reduced, and the training effect and generalization ability of the algorithm are improved; and the deep learning sample enhancement system of the present invention The operation method can directly and greatly improve the model effect without optimizing the algorithm level, and at the same time reduce the invalid workload of image annotation.

Description

technical field [0001] The technical solution described in the present invention belongs to the field of deep learning, and the present invention relates to a deep learning sample enhancement system and its operating method. Background technique [0002] At present, due to the huge amount of parameters of deep learning algorithms, a large number of training samples are required to allow the algorithm to converge. The data is finetune. The role of samples in deep learning algorithms is crucial. The number, quality, diversity, and complexity of samples are directly related to whether the final training model of the algorithm can have a good test effect and whether it has a strong generalization ability. rather than overfitting. [0003] Existing deep learning frameworks such as Caffe, etc., will provide some sample enhancement methods such as random cropping, random expansion, random mirroring, random color transformation, etc., but these methods are all sample enhancements ...

AI Technical Summary

Problems solved by technology

However, if artificial methods are used to subjectively and randomly select video frames from various videos as samples, it will inevitably lead to sample sets full of random uncertainties, it is difficult to sample the best sample distribution, and the workload is huge

Images