lucastabelini/LaneATT
Code for the paper entitled "Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection" (CVPR 2021)
PythonMIT
Issues
- 0
How to train on original image sizes 1280*640?
#139 opened by Byronnar - 1
Who knows how to train my own datasets in this model?Can you give me a normative preocess?
#134 opened by zhangzhongyuan1996 - 1
change np.float
#137 opened by byungjinku - 3
Training on original image sizes
#110 opened by vincent-mayer - 0
"$ python main.py test --exp_name laneatt_r34_tusimple --view all" stops running every time
#138 opened by 0nea - 0
what is self.anchors vs self.anchors_cut
#136 opened by mamamamama123 - 2
why need NMS in training process?
#129 opened by Yzichen - 0
- 2
the pretrained file link is disconnected
#104 opened by xiaominzhen - 2
Test with my own image
#117 opened by yixionghuo - 1
example.yml not find
#133 opened by 1429352509lyh - 1
more efficient way to cut anchor features
#128 opened by ztianlin - 0
EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards-based tools.
#132 opened by yangkunhao2017 - 0
Can the number of detected lane lines be increased, for example, I need to detect 9 lane lines?
#131 opened by 1Xiao1Peng1 - 0
why proposals match targets always zero ?
#130 opened by rolyeMMlin - 2
nms is not callable
#97 opened by Aliweka2020 - 3
- 0
Why does the model not overfit a single image?
#127 opened by karkidaju - 10
Issue with NMS
#115 opened by Wakarox - 3
- 1
how to use pre-trained model to continue trainning?
#119 opened by obitooooo - 1
Why extend the line to the edge of the image
#123 opened by AvinsWang - 6
Need help for using my datas in real-time
#124 opened by Wakarox - 1
FPS
#112 opened by liangjxiong - 3
The meaning of nms_topk (nms_topk: 3000) of train_parameters in config file?
#114 opened by sjtuljw520 - 1
How to Generate Video for Culane
#116 opened by Harry-s-Purba - 1
RuntimeError: CUDA error: device-side assert triggered
#121 opened by 987410 - 1
Failed to install nms
#122 opened by liangjxiong - 0
RuntimeError: copy_if failed to synchronize: cudaErrorAssert: device-side assert triggered ON CUlane dataset
#120 opened by Galaxy202020 - 1
CUDA error when training on TuSimple
#111 opened by anir9 - 2
Question about img = (images[0].cpu().permute(1, 2, 0).numpy() * 255).astype(np.uint8)
#113 opened by JonasLos - 5
A question about compiling nms
#106 opened by GongDianCheng - 1
about the model architecture
#109 opened by ForestWang - 1
About the fps result
#108 opened by 0entropy0 - 2
Anchor configuration parameters
#107 opened by fnobis - 5
用自己的数据集生成anchor的预训练权重
#105 opened by Gooddz1 - 4
NMS replacement
#94 opened by SJLNNU - 2
nms/details.cpython-38-x86_64-linux-gnu.so:udefined symbol:_ZN6caffe28....
#103 opened by GongDianCheng - 6
- 1
Problem with the masks
#100 opened by pepesouza81 - 2
multi-gpu training
#96 opened by Sephirex-X - 6
Infer on own data
#89 opened by Christin95 - 1
replace the nms code error
#99 opened by hwang12345 - 1
- 1
the reg_loss is suddenly increace
#93 opened by koughua - 1
Test on custom dataset
#95 opened by fardinayar - 1
A load persistent id instruction was encountered, but no persistent_load function was specified.
#91 opened by xiaoyvlongoing - 4
Ground-truth anntations interpolation
#92 opened by PerceptionGuy - 1
Expected trend for batch_positivies
#90 opened by muragnarok - 1
python set.py install error error!!
#88 opened by shuizaola