harryhan618/SCNN_Pytorch
Pytorch implementation of "Spatial As Deep: Spatial CNN for Traffic Scene Understanding"
PythonMIT
Issues
- 0
训练出来的模型测试时出来的结果全是0
#75 opened by zzstr - 0
训练出来的模型测试时出来的结果全是0
#76 opened by zzstr - 0
训练出来的模型测试时出来的结果全是
#74 opened by zzstr - 0
- 4
- 0
关于代码验证出的准确率和原论文的差异
#72 opened by XXMxxm220 - 38
您好 请教一些问题。非常感谢。
#59 opened by HejhGitHub - 0
车道线检测测试
#71 opened by anhuidinglieqiaodaima - 0
Exception: Some raw_file from your predictions do not exist in the test tasks.
#70 opened by anhuidinglieqiaodaima - 0
failed to detect lanes
#69 opened by wennycooper - 2
About evaluation
#65 opened by chenyiman - 0
About evaluation indicators
#66 opened by miaaaaaaaaaaaaaaaaaaaaaaa - 0
CULane evaluation problem
#64 opened by yezi-yang - 0
- 3
- 1
Segmentation fault
#62 opened by fu123456 - 2
why not use the std and mean values of CULane to do normalization when traing and testing?
#61 opened by XavierNie715 - 5
Run demo_test.py on GPU
#28 opened by maym86 - 3
a question about train.py
#58 opened by foxkw - 1
- 1
- 1
excuse me, may I ask you a couple of questions?
#56 opened by HejhGitHub - 1
- 7
hello
#54 opened by HejhGitHub - 0
- 3
how to test CULane datasets
#44 opened by yuze9542 - 1
how to convert pytorch model to caffe model?
#42 opened by snowflake119 - 0
model performance
#43 opened by souhasouha - 2
请问怎么检测多于4条车道线?
#50 opened by norainnosun - 1
Should decrease the learning rate to avoid huge loss when training with multi-GPU
#47 opened by evakasch - 2
what cfgs used in training on CULane dataset?
#46 opened by zlxu2011 - 1
HI,Can you help me how to test CUlane data
#45 opened by yuze9542 - 2
- 1
lane size must be greater or equal to 2
#39 opened by Ace-Xu - 1
- 4
- 1
- 1
Cannot get the same F-Score using the ckpt
#36 opened by FCInter - 1
- 2
tusimple training stuck at epoch #1
#32 opened by alchemz - 1
- 0
A question during training,help me please
#40 opened by snowflake119 - 2
How to change the optimizer?
#34 opened by ubill88 - 9
A train error on tusimple
#27 opened by ABexit - 9
替换backbone
#25 opened by TonyAlpha12 - 2
the difference of the two "lane_width"?
#33 opened by Bonsen - 1
Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same error when I tried to modify the code to gpu version?
#29 opened by masouduut94 - 2
关于训练
#26 opened by monsterlyg - 5
RuntimeError: CUDA error: out of memory
#24 opened by alchemz - 1
Image Size That SCNN Uses
#23 opened by alchemz