Does docker-version support GPU

[akrea]

Hi

I could not find this info anywhere in the specs: Does the docker-version of the external-model support GPU usage?

If yes: great!!

If no: would it be possible to provide a dockerfile that includes this option?

Background: I do have a perfectly smooth running NC inculding easy update-processes and custom configuration. So I would much prefer not to build an own NC image as I suspect a high probablity of having issues in bringing my current set-up back to life. Another unknown are update/-gradability issues of the self-compiled image. To add the external-model on the same host seems a much safe route to take.

Thanks for clarification!
akrea

[akrea]

• OK - what I found out: the external model does not work with cuda cores.
• In addition, to use the external version one still needs the dlib package on nextcloud installed in order to load the face recognition app.

So I will wait till the docker nextcloud version provides the dlib-package by default. It should happen as soon as dlib is out of its "infant" state.

Still I would prefer to use cuda cores on the external model.

cheers

[KoMa1012]

I was able to get the external model with cuda running on ubuntu, however I didn't document how I did it.

Since I want to get rid of my ubuntu setup I might try to get it running in a docker container, however I have 0 experience with this, so this will take quite some time!

[mrbrdo]

After much testing I managed to make a docker image which works for me in docker:
https://github.com/mrbrdo/facerecognition-external-model-cuda

I am using nvidia driver version 535 on Ubuntu 22.04 with nvidia-container-toolkit (see nvidia install docs)

To use it (port 8090):

cd facerecognition-external-model-cuda
docker build --tag 'facerecognition-external-cuda' .
sudo docker run --rm --runtime=nvidia --gpus all -i -p 8090:5000 -v /PATH/TO/YOUR/api.key:/app/api.key -e FACE_MODEL=4 --name facerecognition-external-cuda facerecognition-external-cuda

[guillebot]

Hi Jan, Matias As I have a huge image collection and a RTX card, I jumped to try this. I was able to build and run the cuda image but when I try to use it with face:background_job, I get this error: ``` CNN_DETECTOR = dlib.cnn_face_detection_model_v1(DETECTOR_PATH) RuntimeError: Error while calling cudaGetDevice(&the_device_id) in file /tmp/pip-wheel-js0yp6db/dlib_666e8ae1fada4f51b17d0e199472f5a8/dlib/cuda/gpu_data.cpp:204. code: 500, reason: named symbol not found ``` Could it be that my installed driver is newer? This is what I get with nvidia-smi on your container: ``` # nvidia-smi Sun May 26 18:04:20 2024 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 560.00 Driver Version: 560.38 CUDA Version: 12.4 | |-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce RTX 2080 ... On | 00000000:01:00.0 On | N/A | | 0% 41C P2 53W / 250W | 3818MiB / 8192MiB | 4% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ thanks a lot

…

On Sat, May 25, 2024 at 9:34 PM Jan Berdajs ***@***.***> wrote: After much testing I managed to make a docker image which works for me in docker: https://github.com/mrbrdo/facerecognition-external-model-cuda I am using nvidia driver version 535 on Ubuntu 22.04 with nvidia-container-toolkit (see nvidia install docs <https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html> ) — Reply to this email directly, view it on GitHub <#6 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAIXVWMT7HSBB2LRQJ4GLS3ZEEUXVAVCNFSM5ZFKKYW2U5DIOJSWCZC7NNSXTN2JONZXKZKDN5WW2ZLOOQ5TEMJTGE4DAMBTGM2Q> . You are receiving this because you are subscribed to this thread.Message ID: <matiasdelellis/facerecognition-external-model/issues/6/2131800335@ github.com>

[guillebot]

Well to add more information, I was able to rebuild the image with

FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04 AS builder

There is no version mismatch anymore, but getting the same error.

Will keep troubleshooting this

regards

[mrbrdo]

@guillebot I'm not sure why you have that issue. Perhaps try with the driver version 535? Is the nvidia-smi output from the host or the container?
I don't think the CUDA version should matter, as long as it is not higher than what nvidia-smi says (that's the max supported version). You could even try with CUDA 11.

[KoMa1012]

After much testing I managed to make a docker image which works for me in docker: https://github.com/mrbrdo/facerecognition-external-model-cuda

I am using nvidia driver version 535 on Ubuntu 22.04 with nvidia-container-toolkit (see nvidia install docs)

To use it (port 8090):

cd facerecognition-external-model-cuda
docker build --tag 'facerecognition-external-cuda' .
sudo docker run --rm --runtime=nvidia --gpus all -i -p 8090:5000 -v /PATH/TO/YOUR/api.key:/app/api.key -e FACE_MODEL=4 --name facerecognition-external-cuda facerecognition-external-cuda

It's Kinda working for me, I can curl host:port/welcome and it returns"{"facerecognition-external-model":"welcome","model":4,"version":"1.0.0"}" However, if I start to recognize faces it's reporting:
"Faces found: 0. Image will be skipped because of the following error: External model response /detect with error. HTTP status code: 412"

I'm running a gtx1070 with driver 560.35.03 but I also tested with v550.120 with the same behavior. Unfortunately I can not switch to 535 since I'm using unraid and driver installation isn't trivial there. Any Ideas if this is related to the driver or what is going on? I can run nvidia-smi within the container and it's outputing information.

Is there any way to get more output than this general error? So, a debugging flag or something would be nice.