A training set evaluation method and system of a neural network model

• Main Author: LUO PEIYUAN
• Format: Patent
• Language: Chinese; English
• Published: 11.12.2018
• Subjects: CALCULATING; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a training set evaluation method and system of a neural network model. The method comprises the following steps: dividing collected original data into a test set and a trainingset according to a preset proportion; preprocessing the test set to obtain the processed file set; normalizing each file in the processed file set; predicting a classification probability of each normalized file using a neural network model trained according to the training set; according to the classification probability of each file, performing classification statistics according to a preset statistical category, and obtaining evaluation information for evaluating the training set. The invention evaluates the advantages and disadvantages of the training set by using the prediction result ofthe test set which is homologous to the training set, realizes the effective positioning, and obtains the evaluation information with high accuracy and quantification. 本发明公开了种神经网络模型的训练集评估方法及系统，该方法包括：将采集的原始数据按照预设比例分为测试集和训练集；对所