ISAR image classification method based on spatial transformation three-channel convolution

The invention discloses an ISAR image classification method based on spatial transformation three-channel convolution, mainly solving the problems that an existing ISAR target classification technology cannot adapt to a complex imaging environment, and ISAR image features are not fully utilized, and the classification precision is low. The ISAR image classification method comprises the following steps: 1) generating a training sample set and a test sample set; 2) constructing an ISAR image classification network based on spatial transformation three-channel convolution; 3) inputting the training sample set into an ISAR image classification network based on spatial transformation three-channel convolution for training; and 4) inputting the test sample set into a trained ISAR image classification network based on spatial transformation three-channel convolution for testing to obtain a classification result output by the network. The ISAR image classification method can effectively correct the spatial transforma