about inference time

[JensenHJS]

I haven‘t look at code detailedly. But is the inference time the same as darknet frame? In official darknet frame,it indeed costs about 300ms to predict one picture.But your unquantized yolov3 algorithm only costs about 20ms. I think they should be approximate. By the way ,I test it in jetson tx2.
I am looking for your reply

[AlexeyAB]

Try to run ./darknet detector test ... without image.jpg at the end of command

And then enter image.jpg and press Enter, repeat several times.

Do it on both frameworks.

And show screenshots of results.