-
Notifications
You must be signed in to change notification settings - Fork 90
"Super Resolution failed" #348
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
Comments
Hmm, strange -- is there a way that you can list all of the CPU details (such as the supported extensions like AVX, etc.) from the VM? The error trace seems like OpenVINO is unable to find an implementation that matches the capabilities of your CPU (this is kind of a guess) -- and so this is why it would be interesting to compare the listed extensions in VM & then host. |
Same for me. At first I thought it's my poor 3rd gen i5 laptop with 4GB memory. But I do get the exact same error on a physical laptop. Ubuntu 24.04 CPU Features:
|
Hmm, let me look into a bit. My guess is that perhaps this error occurs on systems that lack AVX2 support... I'll need to find something to test with. |
Same exact issue here, just a plus much more numbers of the avformat-XX.dll on the error 126, so following the thread o/ |
Hi @Duderine , what kind of CPU are you using? Can you share the model details? |
Hi @RyanMetcalfeInt8 thanks for the reply! Yes, my CPU is Intel i5-3230m 2.60GHz THX :) |
@RyanMetcalfeInt8 Any update in this case? :) |
Same crash here 🙂 Intel(R) Core(TM) i7-3770K CPU @ 3.50GHz 3.50 GHz |
When i try to use the "OpenVINO Super Resolution" in Audacity, i get the following error message:
Here's the log:
05:36:07: Audacity 3.7.1
05:36:07: Error: Failed to load shared library 'avformat-61.dll' (error 126: The specified module could not be found.)
05:36:07: Error: Failed to load shared library 'avformat-60.dll' (error 126: The specified module could not be found.)
05:36:07: FFmpeg libraries loaded successfully from: C:\Program Files\FFmpeg For Audacity\avformat-59.dll
05:36:10: Error: Failed to load shared library 'avformat-61.dll' (error 126: The specified module could not be found.)
05:36:10: Error: Failed to load shared library 'avformat-60.dll' (error 126: The specified module could not be found.)
05:36:10: FFmpeg libraries loaded successfully from: C:\Program Files\FFmpeg For Audacity\avformat-59.dll
05:36:19: File name is C:\Users\mikaelkw\Music\Webbie - Savage Life 2\03 - Independent (feat. Boosie Badazz & Lil Phat).flac
05:36:19: Mime type is *
05:36:19: Opening with libsndfile
05:36:19: Open(C:\Users\mikaelkw\Music\Webbie - Savage Life 2\03 - Independent (feat. Boosie Badazz & Lil Phat).flac) succeeded
05:36:20: Operation 'Importing FLAC (Free Lossless Audio Codec)' took 1.046000 seconds. Poll was called 44 times and took 0.021199 seconds. Yield was called 10 times and took 0.003406 seconds.
05:36:21: Operation 'Music Information Retrieval' took 0.000000 seconds. Poll was called 0 times and took 0.000000 seconds. Yield was called 0 times and took 0.000000 seconds.
05:36:34: Operation 'Pre-processing' took 0.000000 seconds. Poll was called 0 times and took 0.000000 seconds. Yield was called 0 times and took 0.000000 seconds.
05:36:43: Error: In Super Resolution, exception: Exception from src\inference\src\cpp\core.cpp:107:
Exception from src\inference\src\dev\plugin.cpp:53:
Exception from src\plugins\intel_cpu\src\node.cpp:1535:
Unsupported operation of type: GroupNormalization name: __module.diffusion_model.input_blocks.4.0.in_layers.0/aten::group_norm/GroupNormalization
Details:
Exception from src\plugins\intel_cpu\src\nodes\reference.cpp:17:
Not Implemented:
Cannot fallback on ngraph reference implementation (Ngraph::Node::evaluate() is not implemented)
05:36:49: Operation 'OpenVINO Super Resolution' took 9.438000 seconds. Poll was called 20 times and took 0.070924 seconds. Yield was called 19 times and took 0.046365 seconds.
This is the same for both models (Basic (General), Speech).
The error messages only show up when i try to run it in VM's. Why do i run it in VM's? Because i want to setup a renedering farm for upscaling of audio.
When i run the same model's on a "bare metal" server with the same CPU's, i don't get the same error message, and it works just fine.
Details about the VM
OS: Windows 10 22H2
RAM assigned: 128GB
CPU's/CPU cores assigned: 2/16
Details about the host
Model: DL380P gen8
CPU's: 2x Xeon 2690 v2
RAM: 256GB
Hypervisor: ESXi (version 8)
Activated the following on the VM:
Let me know if any other details need to be added.
The text was updated successfully, but these errors were encountered: