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
847 stars 138 forks source link

python file for generation line points and visualization #73

Open RyanHangZhou opened 2 years ago

RyanHangZhou commented 2 years ago

Hey, very impressive work on lane detection. I'm wondering if you could provide a simple file for easy generating line points and its visualization given an arbitrary street scene image? Thanks!

voldemortX commented 2 years ago

@RyanHangZhou Do you mean something like visualizing a line (defined by sample points), on a given image?

voldemortX commented 2 years ago

tools/vis/lane_img_dir.py can visualize CULane format line txts on a folder of images.

RyanHangZhou commented 2 years ago

Yes, I find the configuration of datasets complex to me. I may not need configurating them for training. I'd like to use the model for providing points and its orientations with only a given image.

RyanHangZhou commented 2 years ago

tools/vis/lane_img_dir.py can visualize CULane format line txts on a folder of images.

I also encounter issues like this: File "tools/vis/lane_img_dir.py", line 4, in <module> from importmagician import import_from ModuleNotFoundError: No module named 'importmagician'

Didn't find this importmagician module in the directory ...

voldemortX commented 2 years ago

you'll need to install it via pip install importmagician

voldemortX commented 2 years ago

Yes, I find the configuration of datasets complex to me. I may not need configurating them for training. I'd like to use the model for providing points and its orientations with only a given image.

It is difficult to maintain minimum code for any one exact application, but the present vis code should be in relatively the easiest way, especially when you consider using a model to inference.