Skip to content

Install Trackers

Add multi-object tracking to your detection pipeline with a single install. Works with any detector, any framework.

What you'll learn:

  • Install trackers with pip or uv
  • Set up a local development environment

Requirements

Python 3.10+. Works on Linux, macOS, and Windows.

Quickstart

Get started by installing the package.

pip install trackers

uv pip install trackers

If your project uses uv for dependency management, add trackers directly to your project.

uv add trackers

Install the latest development version directly from GitHub.

pip install git+https://github.com/roboflow/trackers.git

Extras

The base install covers tracking only. Optional extras add functionality like built-in detection.

Detection

The detection extra installs inference-models, enabling the CLI to run detection automatically so you don't need to bring your own model.

pip install "trackers[detection]"

uv pip install "trackers[detection]"

ReID (BoT-SORT appearance)

The reid extra installs the standalone reid package, which brings PyTorch, timm, Hugging Face Hub, safetensors, Pillow, and gdown for ReID model loading (OSNet, FastReID SBS, and timm: backbones) and BoT-SORT appearance association.

pip install "trackers[reid]"

uv pip install "trackers[reid]"

Use via from reid import ReIDModel and BoTSORTTracker(reid_model=...), or via CLI flags such as --reid.enable and --reid.architecture on trackers track command (BoT-SORT only). See the Re-ID guide for loading an encoder and choosing thresholds.

GPU Acceleration

For GPU support, ensure PyTorch is installed with CUDA or MPS.

Tune

The tune extra installs optuna, enabling automated hyperparameter search — see the tune guide.

pip install "trackers[tune]"

uv pip install "trackers[tune]"

Mask

The mask extra installs torch, torchvision, rf-segment-anything, and rf-cutie, enabling the SAM + Cutie mask pipeline used by McByte, trackers inspect, and the mask-conditioned benchmarking commands — see the inspect guide.

pip install "trackers[mask]"

uv pip install "trackers[mask]"

GPU Acceleration

For GPU support, ensure PyTorch is installed with CUDA or MPS.

Development Setup

Set up a local environment for contributing or modifying trackers.

git clone --depth 1 -b develop https://github.com/roboflow/trackers.git
cd trackers

python3.10 -m venv venv
source venv/bin/activate

pip install --upgrade pip
pip install -e "."

git clone --depth 1 -b develop https://github.com/roboflow/trackers.git
cd trackers

uv python pin 3.10
uv sync
uv pip install -e . --all-extras