Open bsubbaraman opened 4 years ago
Currently we're using YOLOv2 for object recognition/tracking. We should upgrade to v3 and make use of transfer learning to be able to retrain on new data without having to retrain the entire network.
Currently we're using YOLOv2 for object recognition/tracking. We should upgrade to v3 and make use of transfer learning to be able to retrain on new data without having to retrain the entire network.