Get started
-
Install with
pip(or another package manager likeuv) from the package index hosted on this site:
This installs the newest release, which is OpenCV 5. OpenCV 5 has breaking API changes (see the upstream change logs); to stay on OpenCV 4.x, ask for a version below 5:pip install opencv-python-cuda --extra-index-url https://breakthrough.github.io/opencv-python-cuda/packages/
Or download thepip install "opencv-python-cuda<5" --extra-index-url https://breakthrough.github.io/opencv-python-cuda/packages/.whlfile from the release above and install it by path:pip install opencv_python_cuda-*-win_amd64.whl -
Verify that CUDA is working:
import cv2 print(cv2.cuda.getCudaEnabledDeviceCount())
By downloading and using the software, you agree to fully comply with the terms and conditions of the CUDA EULA.
About
opencv-python-cuda is a fork of the official opencv-python project that ships CUDA-enabled OpenCV builds with all batteries included: every required runtime library is bundled directly in the wheel, including hardware video decoding and encoding (NVDEC/NVENC).
Two release lines are maintained: OpenCV 5.x (built from the 5.x-cuda branch) and
OpenCV 4.x (built from the 4.x-cuda branch). Both are published to the same package
index, so you can pick either one with a version specifier.
The only system requirement is an up-to-date NVIDIA driver - the wheel links directly
against driver components, so a working driver must be installed for import cv2
to succeed.