Deep learning sample enhancement system and operation method thereof

Abstract

The invention discloses a deep learning sample enhancement system, comprising a video module used for recording and providing a video sequence, a detector used for obtaining an optimized SSD network from the video sequence, a sample module including original samples of labeled data, a sampling module used for carrying out sampling detection and statistical analysis on the video sequence, a screening module, and a labeling module. The invention further discloses an operation method of the deep learning sample enhancement system. Through the deep learning sample enhancement system, training samples are automatically selected, the diversity and complexity of training samples are enhanced, the redundancy of training samples is reduced, and the training effect and generalization ability of thealgorithm are improved. Moreover, the operation method of the deep learning sample enhancement system can directly and significantly improve the model effect without algorithm-level optimization, andcan reduce the invalid workload of image labeling.

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