The invention relates to the technical field of computer vision, in particular to a gait recognition method and system based on space-time slice features, equipment and a storage medium, and the method comprises the steps: associating features from adjacent body parts from top to bottom through a slice extraction device, and learning the weight of each frame through a residual frame attention mechanism, and weighting each frame of the gait contour sequence, so that the network can pay more attention to the frames with high contributions. According to the method and system, a residual frame attention mechanism and slice features are combined in parallel, and key frame screening can be flexibly carried out on each adjacent feature of a human body, so that the method provided by the invention has relatively high gait recognition accuracy under cross view angles and complex conditions; in addition, any number of video frames can be input, and the method and system have the advantages of being simple and flexible in model, wide in application range and good in real-time performance.