Lin Bai

as far as I know, you should assign each channel of each dma an unique device-id. please change accordingly and let me know in case of any further problem.

> Hi, thanks for your sharing code first. > However, when I try your code to realize the velodyne cloud points projection to image, I found there are mismatch between...

any idea why i must be 2?

> > i have not trained this model > > I am training now! How is your training right now? Using the pre-trained Xception or training from scratch?

> @ildoonet First, use torch to generate bfloat16 input: https://pytorch.org/docs/stable/generated/torch.Tensor.bfloat16.html > > Then use IO Bining (search `PyTorch tensor` in the following document): https://onnxruntime.ai/docs/api/python/api_summary.html According to your solution, I wrote...

> Traceback (most recent call last): File "C:\Users\usuario2\Downloads\8086-emulator-master\ui\codeeditor.py", line 150, in paintEvent self.codeEditor.lineNumberAreaPaintEvent(event) File "C:\Users\usuario2\Downloads\8086-emulator-master\ui\codeeditor.py", line 52, in lineNumberAreaPaintEvent painter.drawText(0, top, areaWidth - rightMargin, TypeError: arguments did not match any...