faad3/Railway-Workers-Detection

Object detection of railway workers, their helmets and vests, using Darknet Framework.

Railway-Workers-Detection

Object detection of railway workers, their helmets and vests, using YOLOv4 and Darknet Framework.

Instalation

git clone https://github.com/AlexeyAB/darknet.git
make up 
make in
cd darknet
mkdir build_release
cd build_release
cmake ..
cmake --build . --target install --parallel 8

Download and unzip dataset.zip in /app/dataset.

Download weights unzip and put it in /app/darknet_dataset/backup/ folder.

(Optionaly) Donwload weights of YOLOv4 pretrained on MSCOCO if you want to reproduce training.

Results

mAP@0.5: 98.73%

Inference on your own data

python inference.py -i /full/path/to/input/folder -o /full/path/to/output/folder