Image classification model training method and device, equipment, medium and program product

The invention discloses a training method and device of an image classification model, equipment, a medium and a program product, and belongs to the field of image classification, and the method comprises the steps: obtaining a sample image and at least two label texts; converting the sample image into image features; each label text in the at least two label texts is converted into a corresponding text feature; calculating a feature distance between the image feature and each text feature; and training an image classification model based on the feature distance between the image feature and each text feature. According to the method, by calculating the feature distance between the image feature and each text feature, the image classification model is trained, a prediction result related to semantic information of the tag text is obtained, and compared with a prediction result representing image authenticity through a digital tag, the prediction result of the image classification model can provide more semant