关于deepfacelive的问题请教

我想做琉璃 · 发表于 2022-9-12 16:28:51

星级打分

1
2
3
4
5

平均分:NAN 参与人数:0 我的评分:未评

Running DeepFaceLive.
2 0 2 2 - 0 9 - 1 2 1 6 : 2 7 : 5 9 . 1 5 7 6 9 6 1 [ E : o n n x r u n t i m e : D e f a u l t , c u d a _ c a l l . c c : 1 1 8 o n n x r u n t i m e : : C u d a C a l l ] C U D A f a i l u r e 3 : i n i t i a l i z a t i o n e r r o r ; G P U = 1 6 6 5 2 6 9 7 6 ; h o s t n a m e = D E S K T O P - 5 H E M M 0 0 ; e x p r = c u d a G e t D e v i c e C o u n t ( & n u m _ d e v i c e s ) ;
2 0 2 2 - 0 9 - 1 2 1 6 : 2 8 : 0 2 . 2 3 1 6 2 4 9 [ E : o n n x r u n t i m e : D e f a u l t , c u d a _ c a l l . c c : 1 1 8 o n n x r u n t i m e : : C u d a C a l l ] C U D A f a i l u r e 3 : i n i t i a l i z a t i o n e r r o r ; G P U = 1 5 1 9 9 7 6 4 4 8 ; h o s t n a m e = D E S K T O P - 5 H E M M 0 0 ; e x p r = c u d a G e t D e v i c e C o u n t ( & n u m _ d e v i c e s ) ;
FaceDetector error: D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_execution_provider_info.cc:97 onnxruntime::CUDAExecutionProviderInfo::FromProviderOptions [ONNXRuntimeError] : 1 : FAIL : provider_options_utils.h:153 onnxruntime:

roviderOptionsParser:

arse Failed to parse provider option "device_id": cuda_execution_provider_info.cc:97 onnxruntime::CUDAExecutionProviderInfo::FromProviderOptions::<lambda_279c3dda0d9974770c8af7502367fa5a>:

perator () cudaGetDeviceCount() failed.
Traceback (most recent call last):
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\xlib\mp\csw\CSWBase.py", line 472, in _start_proc
self.on_start(*worker_start_args, **worker_start_kwargs)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\apps\DeepFaceLive\backend\FaceDetector.py", line 87, in on_start
cs.detector_type.select(state.detector_type if state.detector_type is not None else DetectorType.YOLOV5)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\xlib\mp\csw\DynamicSingleSwitch.py", line 99, in select
result = self._set_selected_idx(idx_or_choice)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\xlib\mp\csw\DynamicSingleSwitch.py", line 33, in _set_selected_idx
self._on_selected_evl.call(selected_idx, self.get_selected_choice() )
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\xlib\python\EventListener.py", line 24, in call
func(*args, **kwargs)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\apps\DeepFaceLive\backend\FaceDetector.py", line 105, in on_cs_detector_type
cs.device.select(state.YoloV5_state.device)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\xlib\mp\csw\DynamicSingleSwitch.py", line 99, in select
result = self._set_selected_idx(idx_or_choice)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\xlib\mp\csw\DynamicSingleSwitch.py", line 33, in _set_selected_idx
self._on_selected_evl.call(selected_idx, self.get_selected_choice() )
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\xlib\python\EventListener.py", line 24, in call
func(*args, **kwargs)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\apps\DeepFaceLive\backend\FaceDetector.py", line 150, in on_cs_devices
self.YoloV5Face = onnx_models.YoloV5Face(device)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\modelhub\onnx\YoloV5Face\YoloV5Face.py", line 34, in __init__
self._sess = sess = InferenceSession_with_device(str(path), device_info)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\DeepFaceLive\xlib\onnxruntime\InferenceSession.py", line 34, in InferenceSession_with_device
sess = rt.InferenceSession(onnx_model_or_path, providers=[ (device_ep, ep_flags) ], sess_options=sess_options)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 335, in __init__
self._create_inference_session(providers, provider_options, disabled_optimizers)
  File "D:\DeepFaceLive_NVIDIA_build_05_16_2022\DeepFaceLive_NVIDIA\_internal\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 381, in _create_inference_session
sess.initialize_session(providers, provider_options, disabled_optimizers)
RuntimeError: D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_execution_provider_info.cc:97 onnxruntime::CUDAExecutionProviderInfo::FromProviderOptions [ONNXRuntimeError] : 1 : FAIL : provider_options_utils.h:153 onnxruntime:

roviderOptionsParser:

arse Failed to parse provider option "device_id": cuda_execution_provider_info.cc:97 onnxruntime::CUDAExecutionProviderInfo::FromProviderOptions::<lambda_279c3dda0d9974770c8af7502367fa5a>:

perator () cudaGetDeviceCount() failed.
，这个报错提示要怎解决，弄了好几天了，