LaneSegNet

LaneSegNet copied to clipboard

wrong in the corner and how to visualize bev features?

1

Hi, Recently I try to train lanesegnet on my own dataset, but I find that the predictions are often wrong when the car turns a corner. Did you meet wrong...

Miranda0920

segmentation fault

4

I followed the instruction to setup a conda env and install all package, but when I ran test.sh, I got a segmentation fault. I did some debug and it seems...

spcrobocar

Import Error "import_modules_from_strings(**cfg_dict['custom_imports'])"

5

Hello, when I try to test model provided in the repo, I met some import error. And I have verified my "~/.bashrc" file like another issue mentioned (export PYTHONPATH in...

CaffeeCat

CHILD PROCESS FAILED WITH NO ERROR_FILE

1

When I trained the model, it crashed and said " CHILD PROCESS FAILED WITH NO ERROR_FILE". How can I fix it?

spcrobocar

How can I train and evaluate the model using only one GPU on my computer? Thanks for reply:)

Zeitreisender11

Dear authors, I am following https://mmdetection.readthedocs.io/en/v2.26.0/tutorials/pytorch2onnx.html to export lanesegnet model to ONNX format. However, the config file is quite different from the format that framework can support. Could you give...

anhtr-nguyn

Benchmark

3

Hi, Is is possible for you to provide a benchmark script to measure LaneSegNet's FPS? I'm struggling to reach 14 FPS with an a100. Best regards, Pham

KSonPham

How to convert the result to OpenDRIVE format

1

Thank you for your great work. May I ask how to convert the results to OpenDRIVE format.

charming2992

We observe that in the your code `input_dict['lidar2global_rotation'] = np.array(info['pose']['rotation']), ` How do I get ego2global_rotation and ego2global_translation? Looking forward to your reply, thank you!

LePetitSirius

rockywind