VIDEO CLASSIFICATION MODEL TRAINING METHOD, DEVICE, STORAGE MEDIUM, AND ELECTRONIC DEVICE

摘要

A video classification model training method, a device, a storage medium, and an electronic device. The method comprises: inputting a video file to a video classification model for learning to produce an eigenvector (101); dividing the eigenvector into multiple sub-eigenvectors (102); selecting one sub-eigenvector from the multiple sub-eigenvectors as a target sub-eigenvector (103); and inputting the target sub-eigenvector into the video classification training model for training to produce a final video classification model (104). A part of the eigenvector is captured to serve as the target sub-eigenvector to be inputted to the video classification model for use in training, the size of data inputted and that of data converted are reduced, thus reducing training parameters and increasing training efficiency.