Heterogeneous image matching model training method, matching method and medium

The invention discloses a training method and a matching method of a different-source image matching model, and a medium. The training method comprises the following steps: A, acquiring a training image data set; b, building a heterogeneous image matching network model; c, random selection: randomly intercepting a first screenshot on the first image, and marking key points; processing the first image to obtain a background image; intercepting a second screenshot on the second image, and marking key points; d, performing image channel splicing on the background image and the first screenshot to obtain a first mixed image; performing image channel splicing on the background image and the second screenshot to obtain a second mixed image; and E, inputting the obtained mixed image into the established network for forward reasoning to obtain a plurality of key points and corresponding predicted values, calculating a loss function, and repeating iteration until the loss function is converged to a preset value to obt