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
839 stars 137 forks source link

lane_img_dir.py --pred does it support outputting keypoints txt #71

Closed 514398473 closed 2 years ago

514398473 commented 2 years ago

Hello, my English is not good generate a TXT for each picture

514398473 commented 2 years ago

Hello, it's solved. I modified the vis_utils.py added text output.

voldemortX commented 2 years ago

@514398473 如果你真的需要keypoint的txt文件，culane和llamas的数据集测试推理都存的是txt。但如果你的输入是自己的图片视频之类的，那确实需要改一下code。如果你想给这个框架增加这个功能，欢迎提出PR。