TypeError: 'ValueError' object is not callable，when CUDAExecutionProvider mode #3
Description
run successful when on CPUExecutionProvider mode.
but run error when on CUDAExecutionProvider mode .
error log :
python app.py
/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/pandas/core/computation/expressions.py:21: UserWarning: Pandas requires version '2.8.4' or newer of 'numexpr' (version '2.8.3' currently installed).
from pandas.core.computation.check import NUMEXPR_INSTALLED
2024-08-22 10:06:06,271 - cv2box - INFO - Use default log level: info, or you can set env 'CV_LOG_LEVEL' to debug/info/warning/error/critical
Running on local URL: http://0.0.0.0:5000
To create a public link, set share=True in launch().
warning: det_size is already set in scrfd model, ignore
pfpld ['CUDAExecutionProvider', 'CPUExecutionProvider']
Model warm up done !
[[gpu] onnx 10 times fps: 42.141950004018966]
[[gpu] onnx 10 times fps: 42.45289932084333]
2024-08-22 10:06:25.617085482 [W:onnxruntime:Default, cuda_execution_provider.cc:2310 ConvTransposeNeedFallbackToCPU] Dropping the ConvTranspose node: conv2d_transpose to CPU because it requires asymmetric padding which the CUDA EP currently does not support
2024-08-22 10:06:25.617124996 [W:onnxruntime:Default, cuda_execution_provider.cc:2411 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: ConvTranspose node name: conv2d_transpose
2024-08-22 10:06:25.617650844 [W:onnxruntime:Default, cuda_execution_provider.cc:2310 ConvTransposeNeedFallbackToCPU] Dropping the ConvTranspose node: conv2d_transpose_1 to CPU because it requires asymmetric padding which the CUDA EP currently does not support
2024-08-22 10:06:25.617671885 [W:onnxruntime:Default, cuda_execution_provider.cc:2411 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: ConvTranspose node name: conv2d_transpose_1
2024-08-22 10:06:25.618188729 [W:onnxruntime:Default, cuda_execution_provider.cc:2310 ConvTransposeNeedFallbackToCPU] Dropping the ConvTranspose node: conv2d_transpose_2 to CPU because it requires asymmetric padding which the CUDA EP currently does not support
2024-08-22 10:06:25.618209622 [W:onnxruntime:Default, cuda_execution_provider.cc:2411 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: ConvTranspose node name: conv2d_transpose_2
2024-08-22 10:06:25.618725877 [W:onnxruntime:Default, cuda_execution_provider.cc:2310 ConvTransposeNeedFallbackToCPU] Dropping the ConvTranspose node: conv2d_transpose_3 to CPU because it requires asymmetric padding which the CUDA EP currently does not support
2024-08-22 10:06:25.618746728 [W:onnxruntime:Default, cuda_execution_provider.cc:2411 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: ConvTranspose node name: conv2d_transpose_3
2024-08-22 10:06:25.619162584 [W:onnxruntime:Default, cuda_execution_provider.cc:2310 ConvTransposeNeedFallbackToCPU] Dropping the ConvTranspose node: conv2d_transpose_4 to CPU because it requires asymmetric padding which the CUDA EP currently does not support
2024-08-22 10:06:25.619183908 [W:onnxruntime:Default, cuda_execution_provider.cc:2411 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: ConvTranspose node name: conv2d_transpose_4
2024-08-22 10:06:25.619586327 [W:onnxruntime:Default, cuda_execution_provider.cc:2310 ConvTransposeNeedFallbackToCPU] Dropping the ConvTranspose node: conv2d_transpose_5 to CPU because it requires asymmetric padding which the CUDA EP currently does not support
2024-08-22 10:06:25.619602145 [W:onnxruntime:Default, cuda_execution_provider.cc:2411 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: ConvTranspose node name: conv2d_transpose_5
xseg ['CUDAExecutionProvider', 'CPUExecutionProvider']
Model warm up done !
[[gpu] onnx 10 times fps: 3.398418237666232]
[[gpu] onnx 10 times fps: 3.8644535658839736]
9O ['CUDAExecutionProvider', 'CPUExecutionProvider']
Model warm up done !
[[gpu] onnx 10 times fps: 4.281553497165233]
[[gpu] onnx 10 times fps: 5.184034725818552]
warning: det_size is already set in scrfd model, ignore
Traceback (most recent call last):
File "/share/ai/ReHiFace-S-main/face_detect/face_align_68.py", line 200, in init
self.ort_session = ort.InferenceSession(onnx_path)
File "/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 360, in init
self._create_inference_session(providers, provider_options, disabled_optimizers)
File "/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 388, in _create_inference_session
raise ValueError(
ValueError: This ORT build has ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'] enabled. Since ORT 1.9, you are required to explicitly set the providers parameter when instantiating InferenceSession. For example, onnxruntime.InferenceSession(..., providers=['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'], ...)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/gradio/queueing.py", line 536, in process_events
response = await route_utils.call_process_api(
File "/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/gradio/route_utils.py", line 288, in call_process_api
output = await app.get_blocks().process_api(
File "/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/gradio/blocks.py", line 1931, in process_api
result = await self.call_function(
File "/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/gradio/blocks.py", line 1516, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
File "/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2177, in run_sync_in_worker_thread
return await future
File "/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 859, in run
result = context.run(func, *args)
File "/opt/miniconda3/envs/ReHiFace/lib/python3.10/site-packages/gradio/utils.py", line 826, in wrapper
response = f(*args, **kwargs)
File "/share/ai/ReHiFace-S-main/app.py", line 106, in process_image_video
initialize_processor()
File "/share/ai/ReHiFace-S-main/app.py", line 24, in initialize_processor
processor = FaceSwapProcessor(crop_size=opt.input_size)
File "/share/ai/ReHiFace-S-main/app.py", line 32, in init
self.face_alignment = face_alignment_landmark(lm_type=68)
File "/share/ai/ReHiFace-S-main/face_detect/face_align_68.py", line 226, in init
self.fan = pfpld(cpu=False)
File "/share/ai/ReHiFace-S-main/face_detect/face_align_68.py", line 202, in init
raise e("load onnx failed")
TypeError: 'ValueError' object is not callable