microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
https://onnxruntime.ai
MIT License
14.11k stars 2.84k forks source link

DEEPFACE LIVE Issue with onnxruntime_pybind_state. #14667

Open KG-LW opened 1 year ago

KG-LW commented 1 year ago

Describe the issue

Screenshot_20230212_031525 Screenshot 2023-02-12 151428

That's what it says in Face Swapper field and masking is not working.

I've haven't found such problem at any tutorial or article. Here what it says:

2023-02-12 15:16:14.3638931 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:1641 onnxruntime::python::CreateInferencePybindStateModule] Init provider bridge failed.

D:\a_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:574 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/reference/execution-providers/CUDA-ExecutionProvider.html#require

Screenshot_20230212_032207 ments), make sure they're in the PATH, and that your GPU is supported.

That's a screenshot of a folder where is leads in the error message.

To reproduce

If you need clarifing, pls ask. Thanks for help.

Urgency

Urgent

Platform

Windows

OS Version

Windows 11 pro

ONNX Runtime Installation

Built from Source

ONNX Runtime Version or Commit ID

It was downloaded with deepfacelive (i don't understand which version it is)

ONNX Runtime API

Python

Architecture

X64

Execution Provider

CUDA

Execution Provider Library Version

No response

Model File

No response

Is this a quantized model?

Yes

iperov commented 1 year ago

try older geforce drivers

KG-LW commented 1 year ago

try older geforce drivers

Thanks for the answer, I've tried to increase more virtual space till 50gb, and to change the folder location of the soft, which helped.