dnth / yolov5-deepsparse-blogpost

By the end of this post, you will learn how to: Train a SOTA YOLOv5 model on your own data. Sparsify the model using SparseML quantization aware training, sparse transfer learning, and one-shot quantization. Export the sparsified model and run it using the DeepSparse engine at insane speeds. P/S: The end result - YOLOv5 on CPU at 180+ FPS using on
https://dicksonneoh.com/portfolio/supercharging_yolov5_180_fps_cpu/
53 stars 13 forks source link

Would there be a solution for Yolo segmentation ? #20

Open thusinh1969 opened 1 year ago

thusinh1969 commented 1 year ago

Great stuffs really. But it does support only classification and object detection with YoloV5. Any chance it will support instance segmentation as this is where most lenghty latency come from.

Thanks, Steve

dnth commented 1 year ago

This depends on the team behind DeepSparse. Have you tried asking in their Slack?