Skip to content

Releases: cudawarped/opencv-python-cuda-wheels

4.11.0.20250124

24 Jan 18:40
@cudawarped cudawarped
4.11.0.20250124
255564a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
4.11.0.20250124 Latest
Latest

OpenCV python wheels built against CUDA 12.8, Nvidia Video Codec SDK 12.2 and cuDNN 9.7.0.

Suitable for all devices of compute capability >= 5.0 with binary compatible code for devices of compute capability 5.0-12.0.

Nvidia GPU Computing Toolkit v12.8 is required for import cv2 to work and cuDNN 9.7.0 for accelerated inference when using the dnn module.

Note Windows OS: This wheel relies on cuDNN being installed in the CUDA Toolkit directory. Therefore you can either download

  1. the cuDNN Tarball (Version->Tarball) and extract its contents to your CUDA directory, or

  2. the installer (Version->exe (local)) and the add the path to the bin folder inside the cuDNN installation directory to your PATH_TO_PYTHON_DIST/Lib/site-packages/cv2/config.py file. e.g.

    import os

    BINARIES_PATHS = [
    os.path.join('D:/build/opencv/install', 'x64/vc17/bin'),
    os.path.join(os.getenv('CUDA_PATH', 'C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.8'), 'bin')
    os.path.join('C:/Program Files/NVIDIA/CUDNN/v9.7/bin/12.8')
    ] + BINARIES_PATHS

Nvidia CMake configuration output

--   NVIDIA CUDA:                   YES (ver 12.8, CUFFT CUBLAS NVCUVID NVCUVENC)
--     NVIDIA GPU arch:             50 52 60 61 70 75 80 86 89 90 100 120
--     NVIDIA PTX archs:            120
--
--   cuDNN:                         YES (ver 9.7.0)
Build Summary

Windows Build commands

set "CMAKE_ARGS=-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0;10.0;12.0 -DCUDA_ARCH_PTX=12.0"
set ENABLE_CONTRIB=1
set ENABLE_ROLLING=1
python.exe setup.py bdist_wheel --py-limited-api=cp37

Ubuntu 22.04 Build commands

export "CMAKE_ARGS=-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0;10.0;12.0 -DCUDA_ARCH_PTX=12.0"
export ENABLE_CONTRIB=1
export ENABLE_ROLLING=1
python setup.py bdist_wheel --py-limited-api=cp37

Assets 4
Loading

4.11.0.86

16 Jan 08:34
@cudawarped cudawarped
4.11.0.86
764c325
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
4.11.0.86

OpenCV python wheels built against CUDA 12.6, Nvidia Video Codec SDK 12.2 and cuDNN 9.6.0.

Suitable for all devices of compute capability >= 5.0 with binary compatible code for devices of compute capability 5.0-9.0.

Nvidia GPU Computing Toolkit v12.6 is required for import cv2 to work and cuDNN 9.6.0 for accelerated inference when using the dnn module.

Note Windows OS: This wheel relies on cuDNN being installed in the CUDA Toolkit directory. Therefore you can either download

  1. the cuDNN Tarball (Version->Tarball) and extract its contents to your CUDA directory, or

  2. the installer (Version->exe (local)) and the add the path to the bin folder inside the cuDNN installation directory to your PATH_TO_PYTHON_DIST/Lib/site-packages/cv2/config.py file. e.g.

    import os

    BINARIES_PATHS = [
    os.path.join('D:/build/opencv/install', 'x64/vc17/bin'),
    os.path.join(os.getenv('CUDA_PATH', 'C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.6'), 'bin')
    os.path.join('C:/Program Files/NVIDIA/CUDNN/v9.6/bin/12.6')
    ] + BINARIES_PATHS

Build Summary

Windows

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.6, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 60 61 70 75 80 86 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 9.6.0)

Build commands

set "CMAKE_ARGS=-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
set ENABLE_CONTRIB=1
python.exe setup.py bdist_wheel --py-limited-api=cp37

Ubuntu 22.04

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.6, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 53 60 61 62 70 72 75 80 86 87 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 9.6.0)

Build commands

export CMAKE_ARGS="-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;5.3;6.0;6.1;6.2;7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
export ENABLE_CONTRIB=1
python setup.py bdist_wheel --py-limited-api=cp37

Assets 4
Loading

4.10.0.84

24 Jun 14:54
@cudawarped cudawarped
4.10.0.84
cce7c99
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
4.10.0.84

OpenCV python wheels built against CUDA 12.5, Nvidia Video Codec SDK 12.2 and cuDNN 9.2.0.

Suitable for all devices of compute capability >= 5.0 with binary compatible code for devices of compute capability 5.0-9.0.

Nvidia GPU Computing Toolkit v12.5 is required for import cv2 to work and cuDNN 9.2.0 for accelerated inference when using the dnn module.

Note Windows OS: This wheel relies on cuDNN being installed in the CUDA Toolkit directory. Therefore you can either

  1. Download the cuDNN Tarball (not the installer) and extract its contents to your CUDA directory, or

  2. Add the path to the bin folder inside the cuDNN installation directory to your PATH_TO_PYTHON_DIST/Lib/site-packages/cv2/config.py file. e.g.

    import os

    BINARIES_PATHS = [
    os.path.join('D:/build/opencv/install', 'x64/vc17/bin'),
    os.path.join(os.getenv('CUDA_PATH', 'C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5'), 'bin')
    os.path.join('C:/Program Files/NVIDIA/CUDNN/v9.2/bin/12.5')
    ] + BINARIES_PATHS

Build Summary

Windows

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.5, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 60 61 70 75 80 86 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 9.2.0)

Build commands

set "CMAKE_ARGS=-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
set ENABLE_CONTRIB=1
python.exe setup.py bdist_wheel --py-limited-api=cp37

Ubuntu 22.04

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.5, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 53 60 61 62 70 72 75 80 86 87 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 9.2.0)

Build commands

export CMAKE_ARGS="-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;5.3;6.0;6.1;6.2;7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
export ENABLE_CONTRIB=1
python setup.py bdist_wheel --py-limited-api=cp37

Assets 4
Loading

4.10.0.82

03 Jun 19:29
@cudawarped cudawarped
4.10.0.82
5f132ad
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
4.10.0.82

OpenCV python wheels built against CUDA 12.5, Nvidia Video Codec SDK 12.2 and cuDNN 9.1.1.

Suitable for all devices of compute capability >= 5.0 with binary compatible code for devices of compute capability 5.0-9.0.

Nvidia GPU Computing Toolkit v12.5 is required for import cv2 to work and cuDNN 9.1.1 for accelerated inference when using the dnn module.

Note Windows OS: This wheel relies on cuDNN being installed in the CUDA Toolkit directory. Therefore you can either

  1. Download the cuDNN Tarball (not the installer) and extract its contents to your CUDA directory, or

  2. Add the path to the bin folder inside the cuDNN installation directory to your PATH_TO_PYTHON_DIST/Lib/site-packages/cv2/config.py file. e.g.

    import os

    BINARIES_PATHS = [
    os.path.join('D:/build/opencv/install', 'x64/vc17/bin'),
    os.path.join(os.getenv('CUDA_PATH', 'C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.5'), 'bin')
    os.path.join('C:/Program Files/NVIDIA/CUDNN/v9.1/bin/12.5')
    ] + BINARIES_PATHS

Build Summary

Windows

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.5, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 60 61 70 75 80 86 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 9.1.1)

Build commands

set "CMAKE_ARGS=-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
set ENABLE_CONTRIB=1
python.exe setup.py bdist_wheel --py-limited-api=cp37

Ubuntu 22.04

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.5, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 53 60 61 62 70 72 75 80 86 87 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 9.1.1)

Build commands

export CMAKE_ARGS="-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;5.3;6.0;6.1;6.2;7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
export ENABLE_CONTRIB=1
python setup.py bdist_wheel --py-limited-api=cp37

Assets 4
Loading

4.9.80_13/05/24

27 Apr 19:50
@cudawarped cudawarped
4.9.80_13/05/24
8ad8ec1
Compare
Choose a tag to compare
4.9.80_13/05/24

Don't use unless testing fix for opencv/opencv_contrib#3727

OpenCV wheel built against CUDA 12.2, Nvidia Video Codec SDK 12.1 and cuDNN 8.9.7.

Suitable for all devices of compute capability 7.5 and 8.6.

Assets 3
Loading

4.9.0.80_24/04/24

24 Apr 17:07
@cudawarped cudawarped
4.9.0.80_24/04/24
8ad8ec1
Compare
Choose a tag to compare
4.9.0.80_24/04/24

OpenCV python wheel built against CUDA 12.3, Nvidia Video Codec SDK 12.1 and cuDNN 8.9.7.

Suitable for all devices of compute capability >= 5.0 with binary compatible code for devices of compute capability 5.0-9.0.

Nvidia GPU Computing Toolkit v12.3 is required for import cv2 to work and cuDNN 8.9.7 for accelerated inference when using the dnn module.

Build Summary

Windows

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.3, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 60 61 70 75 80 86 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 8.9.7)

Build commands

set "CMAKE_ARGS=-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
set ENABLE_CONTRIB=1
python.exe setup.py bdist_wheel --py-limited-api=cp37

Assets 3
Loading

4.9.0.80

30 Dec 08:28
@cudawarped cudawarped
4.9.0.80
ca13925
Compare
Choose a tag to compare
4.9.0.80

OpenCV python wheels built against CUDA 12.3, Nvidia Video Codec SDK 12.1 and cuDNN 8.9.7.

Suitable for all devices of compute capability >= 5.0 with binary compatible code for devices of compute capability 5.0-9.0.

Nvidia GPU Computing Toolkit v12.3 is required for import cv2 to work and cuDNN 8.9.7 for accelerated inference when using the dnn module.

Build Summary

Windows

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.3, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 60 61 70 75 80 86 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 8.9.7)

Build commands

set "CMAKE_ARGS=-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
set ENABLE_CONTRIB=1
python.exe setup.py bdist_wheel --py-limited-api=cp37

Ubuntu 22.04

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.3, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 53 60 61 62 70 72 75 80 86 87 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 8.9.7)

Build commands

export CMAKE_ARGS="-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;5.3;6.0;6.1;6.2;7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
export ENABLE_CONTRIB=1
python setup.py bdist_wheel --py-limited-api=cp37

Assets 4
Loading

4.8.0.20231027

27 Oct 15:51
@cudawarped cudawarped
4.8.0.20231027
ca13925
Compare
Choose a tag to compare
4.8.0.20231027

OpenCV python wheels built against CUDA 12.3, Nvidia Video Codec SDK 12.1 and cuDNN 8.9.5.

Suitable for all devices of compute capability >= 5.0 with binary compatible code for devices of compute capability 5.0-9.0.

Nvidia GPU Computing Toolkit v12.3 is required for import cv2 to work and cuDNN 8.9.5 for accelerated inference when using the dnn module.

Build Summary

Windows

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.3, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 60 61 70 75 80 86 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 8.9.5)

Build commands

set "CMAKE_ARGS=-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
set ENABLE_CONTRIB=1
set ENABLE_ROLLING=1
python.exe setup.py bdist_wheel --py-limited-api=cp36

Ubuntu 22.04

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.3, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 53 60 61 62 70 72 75 80 86 87 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 8.9.5)

Build commands

export CMAKE_ARGS="-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;5.3;6.0;6.1;6.2;7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
export ENABLE_CONTRIB=1
export ENABLE_ROLLING=1
python setup.py bdist_wheel --py-limited-api=cp36

Assets 4
Loading

4.8.0.20230804

04 Aug 13:46
@cudawarped cudawarped
4.8.0.20230804
43cd716
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
4.8.0.20230804

OpenCV python wheels built against CUDA 12.2, Nvidia Video Codec SDK 12.1 and cuDNN 8.9.3.

Suitable for all devices of compute capability >= 5.0 with binary compatible code for devices of compute capability 5.0-9.0.

Nvidia GPU Computing Toolkit v12.2 is required for import cv2 to work and cuDNN 8.9.3 for accelerated inference when using the dnn module.

Build Summary

Windows

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.2, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 60 61 70 75 80 86 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 8.9.3)

Build commands

set "CMAKE_ARGS=-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
set ENABLE_CONTRIB=1
set ENABLE_ROLLING=1
python.exe setup.py bdist_wheel --py-limited-api=cp36

Linux

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.2, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 53 60 61 62 70 72 75 80 86 87 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 8.9.3)

Build commands

export CMAKE_ARGS="-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;5.3;6.0;6.1;6.2;7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
export ENABLE_CONTRIB=1
export ENABLE_ROLLING=1
python setup.py bdist_wheel --py-limited-api=cp36

Assets 4
Loading

4.8.0.74

02 Jul 15:47
@cudawarped cudawarped
4.8.0.74
0ec125d
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
4.8.0.74

OpenCV python wheels built against CUDA 12.1 Nvidia Video Codec SDK 12.1 and cuDNN 8.9.2.

Suitable for all devices of compute capability >= 5.0 with binary compatible code for devices of compute capability 5.0-9.0.

Nvidia GPU Computing Toolkit v12.1 is required for import cv2 to work and cuDNN 8.9.2 for accelerated inference when using the dnn module.

Build Summary

Windows

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.1, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 60 61 70 75 80 86 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 8.9.2)

Build commands

set "CMAKE_ARGS=-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
set ENABLE_CONTRIB=1
python.exe setup.py bdist_wheel --py-limited-api=cp36

Linux

Nvidia CMake configuration output

NVIDIA CUDA: YES (ver 12.1, CUFFT CUBLAS NVCUVID NVCUVENC)
NVIDIA GPU arch: 50 52 53 60 61 62 70 72 75 80 86 87 89 90
NVIDIA PTX archs: 90

cuDNN: YES (ver 8.9.2)

Build commands

export CMAKE_ARGS="-DWITH_CUDA=ON -DCUDA_ARCH_BIN=5.0;5.2;5.3;6.0;6.1;6.2;7.0;7.2;7.5;8.0;8.6;8.7;8.9;9.0 -DCUDA_ARCH_PTX=9.0"
export ENABLE_CONTRIB=1
python setup.py bdist_wheel --py-limited-api=cp36

Assets 4
Loading