Python OpenCV with Cuda not working after successful build

Question

I am on Windows 10, using Python 3.9.6 and my cv2 version is 4.4.0. I built OpenCV with Cuda successfully and after calling cv2.cuda.getCudaEnabledDeviceCount(), it returns 1 as expected. The following lines also work fine.

net = cv2.dnn.readNetFromCaffe(proto_file, weights_file)
net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA)

# multiple lines
# processing frame
# and setting input blob

net.setInput(in_blob)

However, executing the following line throws an exception.

output = net.forward()

The exception:

cv2.error: OpenCV(4.4.0) G:\opencv-4.4.0\opencv-4.4.0\modules\dnn\src\dnn.cpp:2353: error: (-216:No CUDA support) OpenCV was not built to work with the selected device. Please check CUDA_ARCH_PTX or CUDA_ARCH_BIN in your build configuration. in function 'cv::dnn::dnn4_v20200609::Net::Impl::initCUDABackend'

The message says that my Cuda was not built to work with the selected device (which I'm guessing is my GPU). It seems to have encountered a conflict with CUDA_ARCH_BIN and/or CUDA_ARCH_PTX. My GPU model is NVIDIA Geforce MX130 whose CUDA_ARCH_BIN value is what I found to be 6.1 and I set it according on CMake. How can I resolve these issues? Let me know if I need to provide any more information.

Christoph Rackwitz · Accepted Answer · 2021-09-19 21:52:31Z

4

"Sources say" the MX130 has a Maxwell core, not a Pascal core. Maxwell is the predecessor of Pascal.

Hence, you only have CUDA compute capability 5.0.

You should check that with an appropriate tool such as GPU-Z that does its best to query the hardware instead of going by specs.

Sources:

https://en.wikipedia.org/wiki/GeForce_10_series#GeForce_10_(10xx)_series_for_notebooks (notice how the Fab (nm) is different and the code name is GM108, not GPxxx)
https://www.techpowerup.com/gpu-specs/geforce-mx130.c3043

answered Sep 19, 2021 at 21:52

Christoph Rackwitz

16.4k5 gold badges42 silver badges56 bronze badges

Sign up to request clarification or add additional context in comments.

4 Comments

Kamruzzaman Tauhid Over a year ago

So, should I set CUDA_ARCH_BIN to 5.0? Why does it say 6.1 in most places? I'm a beginner when it comes to GPU hardware specifications.

Robert Crovella Over a year ago

NVIDIA's website says Maxwell (5.x). I was unable to locate any website that indicates that MX130 has compute capability 6.1 (Pascal)

Christoph Rackwitz Over a year ago

yes, in your place I'd try 5.0 now. I think it'll work. the defaults for OpenCV's CUDA modules compile for several compute capabilities, which is also why building OpenCV with CUDA enabled takes so long.

Kamruzzaman Tauhid Over a year ago

I rebuilt it by setting CUDA_ARCH_BIN to 5.0. It worked.

Collectives™ on Stack Overflow

Python OpenCV with Cuda not working after successful build

1 Answer 1

4 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

4 Comments

Your Answer

Sign up or log in

Post as a guest

Related