Remote sensing image classification method and device based on model, equipment and storage medium

The invention discloses a model-based remote sensing image classification method and device, equipment and a storage medium. According to the invention, the to-be-classified remote sensing image is obtained, and then the to-be-classified remote sensing image is classified through the preset remote sensing image scene classification model, so that the category corresponding to the to-be-classified remote sensing image is obtained; the preset remote sensing image scene classification model comprises an extraction layer after an attention module is added in each layer in a preset convolutional neural network, an average pooling layer and a linear classification layer. The remote sensing images to be classified are classified through the preset remote sensing image scene classification model, useless information is effectively filtered and focused on the key scene area by adding the extraction layer of the attention module, dimensionality reduction is performed through the average pooling layer, and the remote se