hodu

> where do you build image? dGPU or Jetson Built by Jetson.

> > Hello, @linghu8812 > > Thank you for good material. When converting the latest version of yolov5.pt to onnx Can I use the yolov5/export_onnx.py you provided? > > Thank...

> this code just for draw rectangles and labels, the rect.x, rect.y means the center x and y of the rect. Why do I need the center of rect when...

> only need left**,** top, width, height left top, width, height ? Thank you.

> Hello, > > Thanks to you, I am looking at good data. >  > When converting to onnx, can it be divided into class information and boxes information...

Hello,  By changing the parameters of the torch.onnx.export function, I got classes and boxes as follows. Why can the dimensions of classes and boxes explain this? And when inferring...

> ((640 / 8) * (640 / 8) + (640 / 16) * (640 / 16) + (640 / 32) * (640 / 32)) * 3 Hello, I don't understand...

> ((640 / 8) * (640 / 8) + (640 / 16) * (640 / 16) + (640 / 32) * (640 / 32)) * 3 I haven't understood this...

> @leeyunhome there are three feature maps output from the net, the `640 / 8` means the width or height of the output feature map. Hello 8, 16, 32 aren't...

> if the image size has changed, shape of the onnx graph should be changed with the same. Hello, When the image size is 640 vs 416 as shown below...