aliyun/conditional-lane-detection issues and pull requests

#74 - Train on own dataset

Issue - State: open - Opened by javierpastorfernandez 2 months ago - 3 comments

#73 - Curvelanes.part1.rar is unable to download

Issue - State: open - Opened by AbdullahJirjees 3 months ago

#72 - Ground truth vs detected lane

Issue - State: open - Opened by NigussieAbate 4 months ago - 5 comments

#71 - The F1 score on the CULane dataset is not as high as reported in the paper.

Issue - State: open - Opened by YiShiyi11 7 months ago

#70 - feat:train mode

Pull Request - State: open - Opened by Tristan20230123 9 months ago - 1 comment

#69 - Error was found in the test code of the CULane-medium.

Issue - State: closed - Opened by sjg918 12 months ago - 2 comments

#68 - Incorrect ground truth due to missing import of MultiLineString

Issue - State: open - Opened by haerrel about 1 year ago - 1 comment

#67 - 为啥执行测试命令也没报错应该是成功检测了但是结果保存和可视化文件是空的呢

Issue - State: open - Opened by yangaiping about 1 year ago - 1 comment

#66 - The implementation details for evaluation procedure

Issue - State: open - Opened by artest08 over 1 year ago

#65 - Tusimple Evaluate, Help!

Issue - State: open - Opened by veronicaisweiwei over 1 year ago - 1 comment

#64 - Results with ResNet-50 and ResNet-101 backbone

Issue - State: open - Opened by zen-d over 1 year ago

#63 - GPU support for A100 or 3090?

Issue - State: open - Opened by XinchaoGou over 1 year ago

#62 - How can l solve this problem？

Issue - State: open - Opened by lovelydjj over 1 year ago - 2 comments

#61 - is ONNX conversion available?

Issue - State: open - Opened by sahamitul over 1 year ago

#60 - 关于clamp_line函数的作用

Issue - State: open - Opened by sumenpuyuan over 1 year ago

#59 - Question about img_norm_cfg

Issue - State: open - Opened by notabigfish over 1 year ago - 2 comments

#58 - Why minus 2.19 in ctnet_head?

Issue - State: closed - Opened by usherbob almost 2 years ago - 1 comment

#57 - tools.condlanenet.common Issue

Issue - State: open - Opened by imadalishah almost 2 years ago

#56 - CondLaneNet on a new Dataset

Issue - State: open - Opened by abdellah-0830 almost 2 years ago - 1 comment

#55 - lane formating bug？

Issue - State: open - Opened by sumenpuyuan almost 2 years ago

#54 - 怎么使用模型检测自己的数据（没有标注

Issue - State: closed - Opened by GongDianCheng about 2 years ago - 7 comments

#53 - aboult albumentation

Issue - State: open - Opened by Ehangiun about 2 years ago

#52 - run

Issue - State: open - Opened by liangjxiong about 2 years ago

#51 - Question about the RIM module?

Issue - State: open - Opened by sjtuljw520 over 2 years ago - 1 comment

#50 - Can't the performance of the algorithm be reproduced on curvelanes?

Issue - State: open - Opened by Jinming-Su over 2 years ago - 2 comments

#49 - Questions about hyper-params

Issue - State: open - Opened by usherbob over 2 years ago

#48 - condlanenet.py

Issue - State: open - Opened by balajiiitg over 2 years ago - 1 comment

#47 - condlanenet.py

Issue - State: open - Opened by balajiiitg over 2 years ago

#46 - CUlane evaluate, help

Issue - State: open - Opened by shuizaola over 2 years ago - 2 comments

#45 - KeyError: 'gt_points' when run the image_demo.py

Issue - State: open - Opened by batuhanbeytekin over 2 years ago - 1 comment

#44 - How to use mmdet API to inference

Issue - State: open - Opened by Bru-Souza over 2 years ago - 2 comments

#43 - how to train five lane lines

Issue - State: open - Opened by jianghongsun over 2 years ago - 1 comment

#42 - There is one case where the lane start point deviates from the lane.

Issue - State: open - Opened by feifeiwei over 2 years ago - 3 comments

#41 - Documentation

Issue - State: closed - Opened by NikolaAndro over 2 years ago - 2 comments

#40 - train

Issue - State: closed - Opened by shuizaola over 2 years ago

#39 - Setup.py develop

Issue - State: open - Opened by NikolaAndro over 2 years ago

#38 - V100推理速度

Issue - State: open - Opened by cedar33 over 2 years ago - 1 comment

#37 - V100的推理速度

Issue - State: open - Opened by cedar33 over 2 years ago

#36 - Frozen ResNet Blocks and BatchNorms

Issue - State: open - Opened by andy-96 over 2 years ago

#35 - Error <THC/THCDeviceUtils.cuh> not found

Issue - State: open - Opened by prabhatkumar95 over 2 years ago - 1 comment

#34 - ValueError: need at least one array to concatenate

Issue - State: open - Opened by wangnian97 over 2 years ago - 1 comment

#33 - Trained culane-small but could not get the performance described in the paper.

Issue - State: open - Opened by KiveeDong over 2 years ago - 26 comments

#32 - results do not agree with the author

Issue - State: closed - Opened by CongerW over 2 years ago - 4 comments

#31 - train --no-validate

Issue - State: open - Opened by hzzzzjzyq over 2 years ago - 3 comments

#30 - RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation

Issue - State: closed - Opened by andy-96 over 2 years ago - 2 comments

#29 - RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that your module has parameters that were not used in producing loss. You can enable unused parameter detection by (1) passing the keyword argument `find_unused_parameters=True` to `torch.nn.parallel.DistributedDataParallel`; (2) making sure all `forward` function outputs participate in calculating loss. If you already have done the above two steps, then the distributed data parallel module wasn't able to locate the output tensors in the return value of your module's `forward` function. Please include the loss function and the structure of the return value of `forward` of your module when reporting this issue (e.g. list, dict, iterable).

Issue - State: open - Opened by FANG-MING almost 3 years ago - 3 comments

#28 - How to inference

Issue - State: open - Opened by rylynchen almost 3 years ago - 1 comment

#27 - row_loss not going down

Issue - State: closed - Opened by sudokhan112 almost 3 years ago

#26 - docker环境的问题

Issue - State: open - Opened by xing12sd almost 3 years ago - 2 comments

#25 - what dose mask_branch in head for?

Issue - State: closed - Opened by Wolfwjs almost 3 years ago

#24 - is it an error in DynamicMaskHead locations

Issue - State: open - Opened by xqpinitial almost 3 years ago

#23 - Need to update the training part of readme file

Issue - State: open - Opened by hyzhou404 almost 3 years ago

#22 - little confusion about sort_line_func

Issue - State: open - Opened by wywywy01 almost 3 years ago

#21 - TypeError: 'DataContainer' object is not subscriptable

Issue - State: closed - Opened by Wolfwjs almost 3 years ago - 1 comment

#20 - add --validate then Error

Issue - State: open - Opened by Wolfwjs almost 3 years ago - 1 comment

#19 - transformer memory not used

Issue - State: open - Opened by Smellly almost 3 years ago

#18 - result of culane when i detect my image is not good

Issue - State: open - Opened by ggyybb almost 3 years ago - 7 comments

#17 - RIM Module

Issue - State: open - Opened by Chen-Albert-FENG almost 3 years ago - 1 comment

#16 - TuSimple Test: The model and loaded state dict do not match exactly.

Issue - State: open - Opened by bsangee08 almost 3 years ago - 5 comments

#15 - 增大batchsize后gpu利用率不稳定，且训练过程会有卡顿

Issue - State: open - Opened by hilnkm almost 3 years ago - 1 comment

#14 - questions about test_curvelanes.py

Issue - State: open - Opened by cedricgsh almost 3 years ago

#13 - export onnx

Issue - State: open - Opened by FlowEternal about 3 years ago - 6 comments

#12 - Could you please tell me how to correct this error？Thank you in advance!!!

Issue - State: closed - Opened by Starboy-at-earth about 3 years ago - 16 comments

#11 - How many GPUs do you use to train CondLaneNet?

Issue - State: open - Opened by Starboy-at-earth about 3 years ago - 1 comment

#10 - RNN head

Issue - State: open - Opened by cuiziteng about 3 years ago - 3 comments

#9 - How to use the official evaluation tools of SCNN to evaluate the results.

Issue - State: open - Opened by qdzwss about 3 years ago - 2 comments

#8 - Running inference

Issue - State: closed - Opened by Tanay0101 about 3 years ago - 3 comments

#7 - TypeError: mask must be numpy array type

Issue - State: open - Opened by feifeiwei about 3 years ago - 4 comments

#6 - Evaluation on CULane

Issue - State: closed - Opened by yushuntang about 3 years ago - 4 comments

#5 - export to onnx

Issue - State: closed - Opened by lucky-xu-1994 about 3 years ago - 9 comments

GitHub / aliyun/conditional-lane-detection issues and pull requests