NeuralFlix
Sparsifying YOLOv5 for 10x Better Performance, 12x Smaller File Size, and Cheaper Deployment
Presenter: Mark Kurtz
Learn how we sparsified (pruned and INT8 quantized) YOLOv5 for a 10x increase in performance and 12x smaller model files. You can do the same with your private data by following the steps outlined on Neural Magic's YOLOv5 model page: neuralmagic.com/yolov5