Remote sensing image extreme value inspection method and device based on deep learning, and medium

The invention discloses a remote sensing image extreme value checking method and device based on deep learning and a medium, and relates to the technical field of remote sensing image processing, and the method comprises the steps: inputting remote sensing image data into a trained checking convolution kernel model, and employing a GPU acceleration calculation method to obtain the position and number of each extreme value point in the remote sensing image data; wherein the training process of checking the convolution kernel model comprises the following steps: acquiring sample remote sensing image data; performing target marking on the sample remote sensing image data to obtain marked sample remote sensing image data; the target comprises the position and the number of each extreme point in the sample remote sensing image data; constructing a remote sensing image data set according to the marked sample remote sensing image data; and training the inspection convolution kernel model based on the remote sensing