FPS Comparision with same specification of YOLOX, YOLOR, YOLOv5 and YOLOv7
GPL-3.0 License
git clone https://github.com/RizwanMunawar/YOLO-RX57-FPS-Comparision.git
cd YOLO-RX57-FPS-Comparision
pip install Cython opencv-python
sudo apt update
sudo apt install build-essential
sudo apt-get install manpages-dev
pip install "git+https://github.com/philferriere/cocoapi.git#egg=pycocotools&subdirectory=PythonAPI"
cd YOLORResearch/yolor
wget https://github.com/RizwanMunawar/YOLO-RX57-FPS-Comparision/releases/download/v0.1.4-release/yolor_p6.pt
cd ..
cd ..
cd YOLOXResearch/YOLOX
wget https://github.com/RizwanMunawar/YOLO-RX57-FPS-Comparision/releases/download/v0.1.4-release/yolox_s.pth
cd ..
cd ..
wget YOLOv7Research/yolov7
wget https://github.com/RizwanMunawar/YOLO-RX57-FPS-Comparision/releases/download/v0.1.4-release/yolov7.pt
cd ..
cd ..
python3 comparision.py --source "2.mp4" --device 0
or
python3 comparision.py --source "2.mp4" --device cpu
python3 comparision.py --source "2.mp4" --device 0 \
--yolov5weights yolov5s.pt --yolorweights yolor_p6.pt \
--yoloxweights yolox_m.pt --yolov7weights yolov7.pt
git clone https://github.com/RizwanMunawar/YOLO-RX57-FPS-Comparision.git
cd YOLO-RX57-FPS-Comparision
pip install pycocotools-windows
Now you will need to download weights of YOLOR, YOLOv7 and YOLOX and move downloaded weights into respective folders. Mentioned steps below to complete this.
Now you can run code with mentioned command below.
python3 comparision.py --source "2.mp4" --device 0
or
python3 comparision.py --source "2.mp4" --device cpu
python3 comparision.py --source "2.mp4" --device 0 \
--yolov5weights yolov5s.pt --yolorweights yolor_p6.pt \
--yoloxweights yolox_m.pt --yolov7weights yolov7.pt
For more details, you can reach out to me on Medium or can connect with me on LinkedIn