LEDNet
LEDNet copied to clipboard
how about the inference speed?
Great work! Is the speed as fast as the paper'value?
The model is built as the paper described. (Only training stragety modified in this implementation) So I think the speed is nearly the same as the paper. (I will test it)
Got it. Thanks.
i run demo.py on GTX 1070, use time 120ms, why it's so slow , the paper said 71FPS.....