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

numpy.linalg.LinAlgError: SVD did not converge #87

Closed wht1712 closed 2 years ago

wht1712 commented 2 years ago

Thanks for the awesome bezier lane detection work. When i use the fcns.get_control_points to generate my own control points, i got the problem "numpy.linalg.LinAlgError: SVD did not converge", do you know the reason? Waiting for your reply, thanks!

voldemortX commented 2 years ago

@wht1712 I don't recall encountering the same error. Do you have input details to repoduce the issue?

wht1712 commented 2 years ago

@voldemortX Sorry to bother you, i have found the bug. Thanks for your quick reply again!