Image classification model training method and device, image classification method and device and electronic equipment

The invention provides an image classification model training method, an image classification method, an image classification device and electronic equipment, which can be applied to the field of image classification and the field of object recognition. The training method comprises the following steps: acquiring a sample image and label data; inputting the sample image into a convolution unit to generate an image feature matrix; performing pulse conversion on elements in the image feature matrix by using a pulse unit to generate a pulse matrix corresponding to the image feature matrix, the pulse convolution layer comprising a convolution unit and a pulse unit; inputting the pulse matrix and the position coding matrix into a pulse self-attention layer, and outputting a down-sampling image corresponding to the sample image; performing image classification according to the down-sampling image to obtain an image classification result; and training an image classification model according to the image classificati