Semantic segmentation model training method, apparatus, computer device, program and storage medium

摘要

The present invention provides a semantic segmentation model training method, apparatus, computer device, program, and storage medium. Among them, the method comprises the steps of constructing a training sample set, inputting the training sample set into a deep network model for training, and inputting the weighting transfer function into the bounding box prediction mask parameters. It includes the steps of training and building a semantic segmentation model. The present invention improves training efficiency.