laitathei

I make the tutorial starting from labeling to training or even inferencing You can watch this video https://www.youtube.com/watch?v=Rff5RhCOj30

I make the tutorial starting from labeling to training or even inferencing You can watch this video https://www.youtube.com/watch?v=Rff5RhCOj30

Yes, I tested with forcing USB2 via https://docs.luxonis.com/en/latest/pages/troubleshooting/#forcing-usb2-communication mentioned method, but it still happen the error. Also, I have provided adequate power supply to power RPI 4 8gb and OAK...

actually, they can support yolov7 now. you can have a look on this https://github.com/luxonis/depthai/issues/779

我之前也遇到這個問題，這是量化過程出錯了

你可以跟我這個repo試一下https://github.com/laitathei/YOLOv8-ONNX-RKNN-Segmentation

你試試混合量化

In the Intel processor, you can only get the simulation result, which can be totally different from the rockchip result When you tried to implement your rknn model into rockchip,...

In the video [https://www.youtube.com/watch?v=Rff5RhCOj30&t=3s&ab_channel=TatHeiLai 4:40](https://youtu.be/Rff5RhCOj30?t=280), the program will show mAP

Do you mean the segmented object pixel area or the area of segmented object in real world scale?