ByteTrack-Sahi

In this repository, the bytetrack tracker is combined with the sahi algorithm.

Download Models

• Download Yolov7-E6E and put it under yolo_models folder

• Download bytetrack_x_mot20 and put it under pretrained folder

Nvidia-Docker2 Installation

distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
      && curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
      && curl -s -L https://nvidia.github.io/libnvidia-container/$distribution/libnvidia-container.list | \
            sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
            sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.listdir

sudo apt-get update

sudo apt-get install -y nvidia-docker2

sudo systemctl restart docker

Docker Commands

Note: Docker-compose version >=1.28

• Install

  sudo docker-compose up --build

• Run

  sudo docker-compose up 

• Close

  sudo docker-compose down

Inference with Docker

Set path first

Open byte_track_sahi/tools/config.py

# at line number 5
path = 'path/to/image/directory'

• ByteTrack Open byte_track_sahi/tools/config.py

# at line number 3
model_to_run = 'norm_yoloX'

• ByteTrack with SAHI (Yolov7) Open byte_track_sahi/tools/config.py

# at line number 3
model_to_run = 'sahi_yolo7'

• ByteTrack with SAHI (YolovX) Open byte_track_sahi/tools/config.py

# at line number 3
model_to_run = 'sahi_yoloX'