An open source lane detection toolbox based on PyTorch

LaneDet

LaneDet is an open source lane detection toolbox based on PyTorch that aims to pull together a wide variety of state-of-the-art lane detection models. Developers can reproduce these SOTA methods and build their own methods.

Benchmark and model zoo

Supported backbones:

• [x] ResNet
• [x] ERFNet
• [x] VGG
• [x] MobileNet

Supported detectors:

• [x] SCNN
• [x] UFLD
• [x] RESA
• [x] LaneATT
• [x] [CondLane] (in branch condlane, will be merged soon)

Installation

Clone this repository

git clone https://github.com/turoad/lanedet.git

We call this directory as $LANEDET_ROOT

Create a conda virtual environment and activate it (conda is optional)

conda create -n lanedet python=3.8 -y
conda activate lanedet

Install dependencies

# Install pytorch firstly, the cudatoolkit version should be same in your system.

conda install pytorch torchvision cudatoolkit=10.1 -c pytorch

# Or you can install via pip
pip install torch torchvision

# Install python packages
python setup.py build develop

Data preparation

CULane

Download CULane. Then extract them to $CULANEROOT. Create link to data directory.

cd $RESA_ROOT
mkdir -p data
ln -s $CULANEROOT data/CULane

For CULane, you should have structure like this:

$CULANEROOT/driver_xx_xxframe    # data folders x6
$CULANEROOT/laneseg_label_w16    # lane segmentation labels
$CULANEROOT/list                 # data lists

Tusimple

Download Tusimple. Then extract them to $TUSIMPLEROOT. Create link to data directory.

cd $RESA_ROOT
mkdir -p data
ln -s $TUSIMPLEROOT data/tusimple

For Tusimple, you should have structure like this:

$TUSIMPLEROOT/clips # data folders
$TUSIMPLEROOT/lable_data_xxxx.json # label json file x4
$TUSIMPLEROOT/test_tasks_0627.json # test tasks json file
$TUSIMPLEROOT/test_label.json # test label json file

For Tusimple, the segmentation annotation is not provided, hence we need to generate segmentation from the json annotation.

python tools/generate_seg_tusimple.py --root $TUSIMPLEROOT
# this will generate seg_label directory

Getting Started

Training

For training, run

python main.py [configs/path_to_your_config] --gpus [gpu_ids]

For example, run

python main.py configs/resa/resa50_culane.py --gpus 0 1 2 3

Testing

For testing, run

python main.py [configs/path_to_your_config] --validate --load_from [path_to_your_model] [gpu_num]

For example, run

python main.py configs/resa/resa50_culane.py --validate --load_from culane_resnet50.pth --gpus 0 1 2 3

Currently, this code can output the visualization result when testing, just add --view.
We will get the visualization result in work_dirs/xxx/xxx/visualization.

For example, run

python main.py configs/resa/resa50_culane.py --validate --load_from culane_resnet50.pth --gpus 0 --view

Inference

See tools/detect.py for detailed information.

python tools/detect.py --help

usage: detect.py [-h] [--img IMG] [--show] [--savedir SAVEDIR]
                 [--load_from LOAD_FROM]
                 config

positional arguments:
  config                The path of config file

optional arguments:
  -h, --help            show this help message and exit
  --img IMG             The path of the img (img file or img_folder), for
                        example: data/*.png
  --show                Whether to show the image
  --savedir SAVEDIR     The root of save directory
  --load_from LOAD_FROM
                        The path of model

To run inference on example images in ./images and save the visualization images in vis folder:

python tools/detect.py configs/resa/resa34_culane.py --img images\
          --load_from resa_r34_culane.pth --savedir ./vis

GitHub

https://github.com/Turoad/lanedet