ROMP icon indicating copy to clipboard operation
ROMP copied to clipboard

Published 20 hours ago • verified publisher icon Arthur151

[Bug] ONNX not working with CUDA

Open vivi90 opened this issue 1 year ago • 4 comments

Steps to reproduce

conda create -n romp python=3.10
conda activate romp
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113
pip install simple-romp cython
romp --mode=webcam --show -t --onnx

Error message

RuntimeError: ... onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "...\onnxruntime_providers_tensorrt.dll"

But the file D:\miniconda3\envs\romp\lib\site-packages\onnxruntime\capi\onnxruntime_providers_tensorrt.dll exists. 🤔

Full error message

To use onnx model, we need to install the onnxruntime python package. Please install it by youself if failed!
Collecting onnxruntime-gpu
  Downloading onnxruntime_gpu-1.12.1-cp310-cp310-win_amd64.whl (110.8 MB)
     ---------------------------------------- 110.8/110.8 MB 4.2 MB/s eta 0:00:00
Collecting coloredlogs
  Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)
     ---------------------------------------- 46.0/46.0 kB 1.2 MB/s eta 0:00:00
Collecting sympy
  Downloading sympy-1.10.1-py3-none-any.whl (6.4 MB)
     ---------------------------------------- 6.4/6.4 MB 8.9 MB/s eta 0:00:00
Collecting protobuf
  Downloading protobuf-4.21.5-cp310-abi3-win_amd64.whl (525 kB)
     ---------------------------------------- 525.5/525.5 kB 5.5 MB/s eta 0:00:00
Collecting flatbuffers
  Using cached flatbuffers-2.0-py2.py3-none-any.whl (26 kB)
Requirement already satisfied: numpy>=1.21.0 in d:\miniconda3\envs\romp\lib\site-packages (from onnxruntime-gpu) (1.23.1)
Requirement already satisfied: packaging in d:\miniconda3\envs\romp\lib\site-packages (from onnxruntime-gpu) (21.3)
Collecting humanfriendly>=9.1
  Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)
     ---------------------------------------- 86.8/86.8 kB 981.5 kB/s eta 0:00:00
Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in d:\miniconda3\envs\romp\lib\site-packages (from packaging->onnxruntime-gpu) (3.0.9)
Collecting mpmath>=0.19
  Downloading mpmath-1.2.1-py3-none-any.whl (532 kB)
     ---------------------------------------- 532.6/532.6 kB 4.2 MB/s eta 0:00:00
Collecting pyreadline3
  Downloading pyreadline3-3.4.1-py3-none-any.whl (95 kB)
     ---------------------------------------- 95.2/95.2 kB 2.7 MB/s eta 0:00:00
Installing collected packages: pyreadline3, mpmath, flatbuffers, sympy, protobuf, humanfriendly, coloredlogs, onnxruntime-gpu
Successfully installed coloredlogs-15.0.1 flatbuffers-2.0 humanfriendly-10.0 mpmath-1.2.1 onnxruntime-gpu-1.12.1 protobuf-4.21.5 pyreadline3-3.4.1 sympy-1.10.1
creating onnx model
Traceback (most recent call last):
  File "D:\miniconda3\envs\romp\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "D:\miniconda3\envs\romp\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "D:\miniconda3\envs\romp\Scripts\romp.exe\__main__.py", line 7, in <module>
  File "D:\miniconda3\envs\romp\lib\site-packages\romp\main.py", line 177, in main
    romp = ROMP(args)
  File "D:\miniconda3\envs\romp\lib\site-packages\romp\main.py", line 67, in __init__
    self._build_model_()
  File "D:\miniconda3\envs\romp\lib\site-packages\romp\main.py", line 87, in _build_model_
    self.ort_session = onnxruntime.InferenceSession(self.settings.model_onnx_path,\
  File "D:\miniconda3\envs\romp\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 347, in __init__
    self._create_inference_session(providers, provider_options, disabled_optimizers)
  File "D:\miniconda3\envs\romp\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 395, in _create_inference_session
    sess.initialize_session(providers, provider_options, disabled_optimizers)
RuntimeError: D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1029 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "D:\miniconda3\envs\romp\lib\site-packages\onnxruntime\capi\onnxruntime_providers_tensorrt.dll"

System

  • OS: Windows 10
  • Cuda: 
    ...
Built on Fri_Dec_17_18:28:54_Pacific_Standard_Time_2021
Cuda compilation tools, release 11.6, V11.6.55
Build cuda_11.6.r11.6/compiler.30794723_0

vivi90 avatar Aug 15 '22 13:08 vivi90

Using CUDA toolkit 11.6 (pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116) instead, did not work.

vivi90 avatar Aug 15 '22 13:08 vivi90

Steps to reproduce

conda create -n romp python=3.10
conda activate romp
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113
pip install simple-romp cython
romp --mode=webcam --show -t --onnx

Error message

RuntimeError: ... onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "...\onnxruntime_providers_tensorrt.dll"

But the file D:\miniconda3\envs\romp\lib\site-packages\onnxruntime\capi\onnxruntime_providers_tensorrt.dll exists. 🤔

Full error message

To use onnx model, we need to install the onnxruntime python package. Please install it by youself if failed!
Collecting onnxruntime-gpu
  Downloading onnxruntime_gpu-1.12.1-cp310-cp310-win_amd64.whl (110.8 MB)
     ---------------------------------------- 110.8/110.8 MB 4.2 MB/s eta 0:00:00
Collecting coloredlogs
  Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)
     ---------------------------------------- 46.0/46.0 kB 1.2 MB/s eta 0:00:00
Collecting sympy
  Downloading sympy-1.10.1-py3-none-any.whl (6.4 MB)
     ---------------------------------------- 6.4/6.4 MB 8.9 MB/s eta 0:00:00
Collecting protobuf
  Downloading protobuf-4.21.5-cp310-abi3-win_amd64.whl (525 kB)
     ---------------------------------------- 525.5/525.5 kB 5.5 MB/s eta 0:00:00
Collecting flatbuffers
  Using cached flatbuffers-2.0-py2.py3-none-any.whl (26 kB)
Requirement already satisfied: numpy>=1.21.0 in d:\miniconda3\envs\romp\lib\site-packages (from onnxruntime-gpu) (1.23.1)
Requirement already satisfied: packaging in d:\miniconda3\envs\romp\lib\site-packages (from onnxruntime-gpu) (21.3)
Collecting humanfriendly>=9.1
  Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)
     ---------------------------------------- 86.8/86.8 kB 981.5 kB/s eta 0:00:00
Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in d:\miniconda3\envs\romp\lib\site-packages (from packaging->onnxruntime-gpu) (3.0.9)
Collecting mpmath>=0.19
  Downloading mpmath-1.2.1-py3-none-any.whl (532 kB)
     ---------------------------------------- 532.6/532.6 kB 4.2 MB/s eta 0:00:00
Collecting pyreadline3
  Downloading pyreadline3-3.4.1-py3-none-any.whl (95 kB)
     ---------------------------------------- 95.2/95.2 kB 2.7 MB/s eta 0:00:00
Installing collected packages: pyreadline3, mpmath, flatbuffers, sympy, protobuf, humanfriendly, coloredlogs, onnxruntime-gpu
Successfully installed coloredlogs-15.0.1 flatbuffers-2.0 humanfriendly-10.0 mpmath-1.2.1 onnxruntime-gpu-1.12.1 protobuf-4.21.5 pyreadline3-3.4.1 sympy-1.10.1
creating onnx model
Traceback (most recent call last):
  File "D:\miniconda3\envs\romp\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "D:\miniconda3\envs\romp\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "D:\miniconda3\envs\romp\Scripts\romp.exe\__main__.py", line 7, in <module>
  File "D:\miniconda3\envs\romp\lib\site-packages\romp\main.py", line 177, in main
    romp = ROMP(args)
  File "D:\miniconda3\envs\romp\lib\site-packages\romp\main.py", line 67, in __init__
    self._build_model_()
  File "D:\miniconda3\envs\romp\lib\site-packages\romp\main.py", line 87, in _build_model_
    self.ort_session = onnxruntime.InferenceSession(self.settings.model_onnx_path,\
  File "D:\miniconda3\envs\romp\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 347, in __init__
    self._create_inference_session(providers, provider_options, disabled_optimizers)
  File "D:\miniconda3\envs\romp\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 395, in _create_inference_session
    sess.initialize_session(providers, provider_options, disabled_optimizers)
RuntimeError: D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1029 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "D:\miniconda3\envs\romp\lib\site-packages\onnxruntime\capi\onnxruntime_providers_tensorrt.dll"

System

  • OS: Windows 10
  • Cuda: 
    ...
Built on Fri_Dec_17_18:28:54_Pacific_Standard_Time_2021
Cuda compilation tools, release 11.6, V11.6.55
Build cuda_11.6.r11.6/compiler.30794723_0

hi, i have same issue,How did you solve it

zhanghongyong123456 avatar Oct 08 '22 06:10 zhanghongyong123456

@zhanghongyong123456

hi, i have same issue,How did you solve it

Still not solved. So using CUDA without ONNX for now.

vivi90 avatar Oct 09 '22 17:10 vivi90