Is that possible to inference more than 4 lanes with the CULane dataset?

Open passion3394 opened this issue 7 years ago • 6 comments

is that possible to inference more than 4 lanes with the CULane dataset? My task needs to detect more than 4 lanes, what should I do if I want to do this task? thanks!!!

Oct 23 '18 01:10 passion3394

@passion3394 , please refer to How to train SCNN on my own dataset #7

Oct 23 '18 02:10 cardwing

@cardwing yes, I have seen the #7 issue, I will try it. Have you tried to inference more than 4 lanes? and what's the precision ?

Oct 23 '18 03:10 passion3394

@passion3394 , the performance depends on the proportion of the number of lanes and the difficulty of road scenarios. I have not tested models predicting more than 4 lanes.

Oct 23 '18 12:10 cardwing

@passion3394 , you can also refer to this repo.

Dec 01 '18 03:12 cardwing

@cardwing ok, thanks for your work.

Dec 02 '18 11:12 passion3394

@passion3394 , you are welcome.

Dec 03 '18 07:12 cardwing