-
Notifications
You must be signed in to change notification settings - Fork 447
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
ImportError: libcuda.so.1: cannot open shared object file: No such file or directory #32
Comments
You can‘t use the predict script with GPUs. What kind of GPU do you have? Did you set up nvidia-docker?? |
I have TensorBook with RTX 2080 GPU. I have done the following step, are there the other steps need to be done?
|
Yes, other steps are required. As I asked before - did you set up nvidia-docker yet?? This article might be helpful https://medium.com/@amaan.ngp/installation-setup-of-nvidia-geforce-rtx-2080ti-cuda-10-1-15fa6c8f8ecb |
I build the Docker image
nima-gpu
withdocker build -t nima-gpu . -f Dockerfile.gpu
But when I score a demo image with
nima-gpu
, I get a Traceback:./predict --docker-image nima-gpu --base-model-name MobileNet --weights-file $(pwd)/models/MobileNet/weights_mobilenet_technical_0.11.hdf5 --image-source $(pwd)/src/tests/test_images/42039.jpg
How could I make this correct? Thanks.
The text was updated successfully, but these errors were encountered: