{"id":13443497,"url":"https://github.com/cfzd/Ultra-Fast-Lane-Detection","last_synced_at":"2025-03-20T16:31:30.518Z","repository":{"id":37625914,"uuid":"266319758","full_name":"cfzd/Ultra-Fast-Lane-Detection","owner":"cfzd","description":"Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)","archived":false,"fork":false,"pushed_at":"2022-12-14T06:50:09.000Z","size":164,"stargazers_count":1774,"open_issues_count":94,"forks_count":492,"subscribers_count":27,"default_branch":"master","last_synced_at":"2024-08-01T03:43:47.255Z","etag":null,"topics":["autonomous-driving","autonomous-vehicles","cnn","lane-detection","lane-detector","lane-finding","pytorch","road-detection"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cfzd.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-05-23T11:11:34.000Z","updated_at":"2024-07-29T05:53:29.000Z","dependencies_parsed_at":"2023-01-28T18:45:58.568Z","dependency_job_id":null,"html_url":"https://github.com/cfzd/Ultra-Fast-Lane-Detection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cfzd%2FUltra-Fast-Lane-Detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cfzd%2FUltra-Fast-Lane-Detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cfzd%2FUltra-Fast-Lane-Detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cfzd%2FUltra-Fast-Lane-Detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cfzd","download_url":"https://codeload.github.com/cfzd/Ultra-Fast-Lane-Detection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221780006,"owners_count":16879040,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["autonomous-driving","autonomous-vehicles","cnn","lane-detection","lane-detector","lane-finding","pytorch","road-detection"],"created_at":"2024-07-31T03:02:02.159Z","updated_at":"2024-10-28T04:31:10.153Z","avatar_url":"https://github.com/cfzd.png","language":"Python","funding_links":[],"categories":["Python","对象检测、分割"],"sub_categories":["网络服务_其他"],"readme":"# Ultra-Fast-Lane-Detection\nPyTorch implementation of the paper \"[Ultra Fast Structure-aware Deep Lane Detection](https://arxiv.org/abs/2004.11757)\".\n\n**\\[July 18, 2022\\] Updates: The new version of our method has been accepted by TPAMI 2022. Code is available [here](https://github.com/cfzd/Ultra-Fast-Lane-Detection-v2)**.\n\n\\[June 28, 2021\\] Updates: we will release an extended version, which improves **6.3** points of F1 on CULane with the ResNet-18 backbone compared with the ECCV version.\n\nUpdates: Our paper has been accepted by ECCV2020.\n\n![alt text](vis.jpg \"vis\")\n\nThe evaluation code is modified from [SCNN](https://github.com/XingangPan/SCNN) and [Tusimple Benchmark](https://github.com/TuSimple/tusimple-benchmark).\n\nCaffe model and prototxt can be found [here](https://github.com/Jade999/caffe_lane_detection).\n\n# Demo \n\u003ca href=\"http://www.youtube.com/watch?feature=player_embedded\u0026v=lnFbAG3GBN4\n\" target=\"_blank\"\u003e\u003cimg src=\"http://img.youtube.com/vi/lnFbAG3GBN4/0.jpg\" \nalt=\"Demo\" width=\"240\" height=\"180\" border=\"10\" /\u003e\u003c/a\u003e\n\n\n# Install\nPlease see [INSTALL.md](./INSTALL.md)\n\n# Get started\nFirst of all, please modify `data_root` and `log_path` in your `configs/culane.py` or `configs/tusimple.py` config according to your environment. \n- `data_root` is the path of your CULane dataset or Tusimple dataset. \n- `log_path` is where tensorboard logs, trained models and code backup are stored. ***It should be placed outside of this project.***\n\n\n\n***\n\nFor single gpu training, run\n```Shell\npython train.py configs/path_to_your_config\n```\nFor multi-gpu training, run\n```Shell\nsh launch_training.sh\n```\nor\n```Shell\npython -m torch.distributed.launch --nproc_per_node=$NGPUS train.py configs/path_to_your_config\n```\nIf there is no pretrained torchvision model, multi-gpu training may result in multiple downloading. You can first download the corresponding models manually, and then restart the multi-gpu training.\n\nSince our code has auto backup function which will copy all codes to the `log_path` according to the gitignore, additional temp file might also be copied if it is not filtered by gitignore, which may block the execution if the temp files are large. So you should keep the working directory clean.\n***\n\nBesides config style settings, we also support command line style one. You can override a setting like\n```Shell\npython train.py configs/path_to_your_config --batch_size 8\n```\nThe ```batch_size``` will be set to 8 during training.\n\n***\n\nTo visualize the log with tensorboard, run\n\n```Shell\ntensorboard --logdir log_path --bind_all\n```\n\n# Trained models\nWe provide two trained Res-18 models on CULane and Tusimple.\n\n|  Dataset | Metric paper | Metric This repo | Avg FPS on GTX 1080Ti |    Model    |\n|:--------:|:------------:|:----------------:|:-------------------:|:-----------:|\n| Tusimple |     95.87    |       95.82      |         306         | [GoogleDrive](https://drive.google.com/file/d/1WCYyur5ZaWczH15ecmeDowrW30xcLrCn/view?usp=sharing)/[BaiduDrive(code:bghd)](https://pan.baidu.com/s/1Fjm5yVq1JDpGjh4bdgdDLA) |\n|  CULane  |     68.4     |       69.7       |         324         | [GoogleDrive](https://drive.google.com/file/d/1zXBRTw50WOzvUp6XKsi8Zrk3MUC3uFuq/view?usp=sharing)/[BaiduDrive(code:w9tw)](https://pan.baidu.com/s/19Ig0TrV8MfmFTyCvbSa4ag) |\n\nFor evaluation, run\n```Shell\nmkdir tmp\n# This a bad example, you should put the temp files outside the project.\n\npython test.py configs/culane.py --test_model path_to_culane_18.pth --test_work_dir ./tmp\n\npython test.py configs/tusimple.py --test_model path_to_tusimple_18.pth --test_work_dir ./tmp\n```\n\nSame as training, multi-gpu evaluation is also supported.\n\n# Visualization\n\nWe provide a script to visualize the detection results. Run the following commands to visualize on the testing set of CULane and Tusimple.\n```Shell\npython demo.py configs/culane.py --test_model path_to_culane_18.pth\n# or\npython demo.py configs/tusimple.py --test_model path_to_tusimple_18.pth\n```\n\nSince the testing set of Tusimple is not ordered, the visualized video might look bad and we **do not recommend** doing this.\n\n# Speed\nTo test the runtime, please run\n```Shell\npython speed_simple.py  \n# this will test the speed with a simple protocol and requires no additional dependencies\n\npython speed_real.py\n# this will test the speed with real video or camera input\n```\nIt will loop 100 times and calculate the average runtime and fps in your environment.\n\n# Citation\n\n```BibTeX\n@InProceedings{qin2020ultra,\nauthor = {Qin, Zequn and Wang, Huanyu and Li, Xi},\ntitle = {Ultra Fast Structure-aware Deep Lane Detection},\nbooktitle = {The European Conference on Computer Vision (ECCV)},\nyear = {2020}\n}\n\n@ARTICLE{qin2022ultrav2,\n  author={Qin, Zequn and Zhang, Pengyi and Li, Xi},\n  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, \n  title={Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification}, \n  year={2022},\n  volume={},\n  number={},\n  pages={1-14},\n  doi={10.1109/TPAMI.2022.3182097}\n}\n```\n\n# Thanks\nThanks zchrissirhcz for the contribution to the compile tool of CULane, KopiSoftware for contributing to the speed test, and ustclbh for testing on the Windows platform.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcfzd%2FUltra-Fast-Lane-Detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcfzd%2FUltra-Fast-Lane-Detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcfzd%2FUltra-Fast-Lane-Detection/lists"}