Unsupervised image classification model training method and device and electronic equipment

The embodiment of the invention discloses an unsupervised image classification model training method and device, and electronic equipment. The method comprises the following steps: inputting an obtained target domain data set and at least one source domain data set into an unsupervised image classification model in batches for processing; training a feature generation network, a classification network, a domain discrimination network and a joint label classification network of the unsupervised image classification model; in response to that corresponding losses of the characteristic generationnetwork, the classification network, the domain discrimination network and the joint label classification network satisfy a predetermined condition, determining that the training of the unsupervisedimage classification model is completed; therefore, according to the embodiment of the invention, the target domain data set and the source domain data set are enabled to realize feature alignment ondomain distribution and category distribution by combining the label classification network, and the classification accuracy of the trained unsupervised image classification model is improved.