Example Jupyter-Notebook file for the detection of lanes using the ultra fast lane detection model in Pytorch.
Source: https://www.flickr.com/photos/32413914@N00/1475776461/
- OpenCV, Scikit-learn and pytorch.
# conda install pytorch torchvision torchaudio cudatoolkit=10.1 -c pytorch
# conda create --name pytorch-gpu-cuda10.1 **-c pytorch** pytorch torchvision cudatoolkit=10.1 jupyterlab scikit-learn opencv
cd workspace/github/Ultrafast-Lane-Detection-Inference-Pytorch-
conda info --envs
conda activate pytorch-gpu-cuda10.1
jupyter-lab
cd Downloads\CARLA_0.9.12\WindowsNoEditor
CarlaUE4 /Game/Carla/Maps/Town03 -windowed -ResX=256 -ResY=128 -carla-port=3000 -benchmark -fps=30 -quality-level=Epic
pip install carla
Pytorch: Check the Pytorch website to find the best method to install Pytorch in your computer.
Download the pretrained model from the original repository and save it into the models folder.
Ultra fast lane detection - TuSimple(link)
- Input: RGB image of size 1280 x 720 pixels.
- Output: Keypoints for a maximum of 4 lanes (left-most lane, left lane, right lane, and right-most lane).
- Carla RGB Cam inference:
carlaLaneDetection.ipynb
Original video: https://youtu.be/2CIxM7x-Clc (by Yunfei Guo)