Picture category prediction method and device, storage medium and electronic equipment

The invention relates to a picture category prediction method and device, a storage medium and electronic equipment, and the method comprises the steps: extracting a feature vector through a convolutional neural network layer according to a sample picture set; performing batch normalization and full connection layer processing on the feature vector by using a batch normalization layer to obtain an Euclidean space feature vector; projection is carried out in the hyperbolic space, and a hyperbolic space category feature vector set of each category is obtained based on category labels corresponding to hyperbolic space feature vectors obtained through projection; based on a contrast loss function and the hyperbolic space category feature vector set, acquiring contrast loss, and according to the contrast loss, adjusting model parameters of a convolutional neural backbone network model comprising a convolutional neural network layer, a batch normalization layer and a full connection layer; and aiming at the sample