Method and device for automatically adjusting hyper-parameters of network model

The embodiment of the invention discloses a method and device for automatically adjusting hyper-parameters of a network model. The method comprises the following steps: dividing a data set to be tested into a training set, a test set and a verification set; performing iterative training on the network model according to the training set to obtain a hyper-parameter model; testing currently obtainedhyper-parameters through the test set in the iterative training process so as to determine whether a preset test result can be obtained according to the hyper-parameters; and verifying the obtained hyper-parameter model after the iterative training is ended so as to determine whether a preset verification result can be obtained according to the hyper-parameter model. According to the embodiment scheme, the optimization efficiency of the hyper-parameters is improved, and the manual setting fee time-consuming operation is avoided. 本发明实施例公开了种自动调节网络模型超参数的方法和装置，该方法包括：将待测试的数据集划分为训练集、测试集和验证集；根据训练集对网络模型进行迭代训练，以获取超参数模型；在迭代训练过