search

voldemortX / pytorch-auto-drive

PytorchAutoDrive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, RESA, LSTR, LaneATT, BézierLaneNet...) based on PyTorch with fast training, visualization, benchmarking & deployment help
BSD 3-Clause "New" or "Revised" License
837 stars 137 forks source link

About the data preprocessing #78

Closed huanFigure closed 2 years ago

huanFigure commented 2 years ago

I follow the README step by step to prepare the CULane dataset, and I have download the CULane dataset successfully. But when I perform the 'make' in 4.Prepare official evaluation scripts of the docs/datasets/CULANE.md ,I always get the fault about 'ln opencv_imgproc' ,which edition of the opencv ,is there someone completed the CULane dataset prepare?

voldemortX commented 2 years ago

@huanFigure

If you are using opencv3, get rid of the if here and just keep L21. If not delete them, it should work 1 of the 2 ways. https://github.com/voldemortX/pytorch-auto-drive/blob/ca81e992794b090dca088df7ad8defed239e24a6/tools/culane_evaluation/Makefile#L20

The process should be automatic, but sometimes your system can't get opencv version (that really happens a lot these days), and it can't be executed.

voldemortX commented 2 years ago

I've updated the code (removed automatic version check) to make things clear.

huanFigure commented 2 years ago

It's worked,thank you very much

voldemortX commented 2 years ago

You're welcome. Since this issue is resolved, I'll close this issue for now.