mmdeploy
mmdeploy copied to clipboard
open-mmlab
[Bug] C# code with failed to create model: not supported (2)
Checklist
- [X] I have searched related issues but cannot get the expected help.
- [X] 2. I have read the FAQ documentation but cannot get the expected help.
- [X] 3. The bug has not been fixed in the latest version.
Describe the bug
When I use the demo code of mmdeploy C# to infer the onnx CPU model, the error is as shown in the figure
Reproduction
Environment
C:\ProgramData\miniconda3\python.exe D:\projects_old\mmdeploy\tools\check_env.py
01/10 10:13:26 - mmengine - INFO -
01/10 10:13:26 - mmengine - INFO - **********Environmental information**********
01/10 10:13:27 - mmengine - INFO - sys.platform: win32
01/10 10:13:27 - mmengine - INFO - Python: 3.11.5 | packaged by Anaconda, Inc. | (main, Sep 11 2023, 13:26:23) [MSC v.1916 64 bit (AMD64)]
01/10 10:13:27 - mmengine - INFO - CUDA available: True
01/10 10:13:27 - mmengine - INFO - numpy_random_seed: 2147483648
01/10 10:13:27 - mmengine - INFO - GPU 0: NVIDIA GeForce RTX 3060
01/10 10:13:27 - mmengine - INFO - CUDA_HOME: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4
01/10 10:13:27 - mmengine - INFO - NVCC: Cuda compilation tools, release 12.4, V12.4.131
01/10 10:13:27 - mmengine - INFO - GCC: n/a
01/10 10:13:27 - mmengine - INFO - PyTorch: 2.1.2+cu121
01/10 10:13:27 - mmengine - INFO - PyTorch compiling details: PyTorch built with:
- C++ Version: 199711
- MSVC 192930151
- Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v3.1.1 (Git Hash 64f6bcbcbab628e96f33a62c3e975f8535a7bde4)
- OpenMP 2019
- LAPACK is enabled (usually provided by MKL)
- CPU capability usage: AVX2
- CUDA Runtime 12.1
- NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
- CuDNN 8.8.1 (built against CUDA 12.0)
- Magma 2.5.4
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.1, CUDNN_VERSION=8.8.1, CXX_COMPILER=C:/actions-runner/_work/pytorch/pytorch/builder/windows/tmp_bin/sccache-cl.exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /bigobj /FS -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE /utf-8 /wd4624 /wd4068 /wd4067 /wd4267 /wd4661 /wd4717 /wd4244 /wd4804 /wd4273, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=OFF, TORCH_VERSION=2.1.2, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=OFF, USE_OPENMP=ON, USE_ROCM=OFF,
01/10 10:13:27 - mmengine - INFO - TorchVision: 0.16.2+cu121
01/10 10:13:27 - mmengine - INFO - OpenCV: 4.8.1
01/10 10:13:27 - mmengine - INFO - MMEngine: 0.10.1
01/10 10:13:27 - mmengine - INFO - MMCV: 2.1.0
01/10 10:13:27 - mmengine - INFO - MMCV Compiler: MSVC 192930148
01/10 10:13:27 - mmengine - INFO - MMCV CUDA Compiler: 12.1
01/10 10:13:27 - mmengine - INFO - MMDeploy: 1.3.1+cabd761
01/10 10:13:27 - mmengine - INFO -
01/10 10:13:27 - mmengine - INFO - **********Backend information**********
01/10 10:13:27 - mmengine - INFO - tensorrt: 8.6.1
01/10 10:13:27 - mmengine - INFO - tensorrt custom ops: Available
01/10 10:13:27 - mmengine - INFO - ONNXRuntime: 1.20.1
01/10 10:13:27 - mmengine - INFO - ONNXRuntime-gpu: None
01/10 10:13:27 - mmengine - INFO - ONNXRuntime custom ops: Available
01/10 10:13:27 - mmengine - INFO - pplnn: None
01/10 10:13:27 - mmengine - INFO - ncnn: None
01/10 10:13:27 - mmengine - INFO - snpe: None
01/10 10:13:27 - mmengine - INFO - openvino: 2023.2.0
01/10 10:13:27 - mmengine - INFO - torchscript: 2.1.2+cu121
01/10 10:13:27 - mmengine - INFO - torchscript custom ops: NotAvailable
01/10 10:13:27 - mmengine - INFO - rknn-toolkit: None
01/10 10:13:27 - mmengine - INFO - rknn-toolkit2: None
01/10 10:13:27 - mmengine - INFO - ascend: None
01/10 10:13:27 - mmengine - INFO - coreml: None
01/10 10:13:27 - mmengine - INFO - tvm: None
01/10 10:13:27 - mmengine - INFO - vacc: None
01/10 10:13:27 - mmengine - INFO -
01/10 10:13:27 - mmengine - INFO - **********Codebase information**********
01/10 10:13:27 - mmengine - INFO - mmdet: 3.2.0
01/10 10:13:27 - mmengine - INFO - mmseg: 1.2.2
01/10 10:13:27 - mmengine - INFO - mmpretrain: 1.2.0
01/10 10:13:27 - mmengine - INFO - mmocr: None
01/10 10:13:27 - mmengine - INFO - mmagic: None
01/10 10:13:27 - mmengine - INFO - mmdet3d: None
01/10 10:13:27 - mmengine - INFO - mmpose: 1.1.0
01/10 10:13:27 - mmengine - INFO - mmrotate: None
01/10 10:13:27 - mmengine - INFO - mmaction: None
01/10 10:13:27 - mmengine - INFO - mmrazor: None
01/10 10:13:27 - mmengine - INFO - mmyolo: None
进程已结束，退出代码为 0
Error traceback
loading mmdeploy_ort_net.dll ...
[2025-01-10 09:56:14.971] [mmdeploy] [info] [zip_model_impl.cpp:38] Failed to open zip file D:\projects_old\mmdeploy\work_dir\chaosheng\epoch_12.onnx, ret 19
[2025-01-10 09:56:14.971] [mmdeploy] [error] [model.cpp:40] Failed to load model: "D:\projects_old\mmdeploy\work_dir\chaosheng\epoch_12.onnx", implementations tried: [("DirectoryModel", 0), ("ZipModel", 0)]
[2025-01-10 09:56:14.971] [mmdeploy] [error] [model.cpp:16] Failed to load model "D:\projects_old\mmdeploy\work_dir\chaosheng\epoch_12.onnx"
[2025-01-10 09:56:14.972] [mmdeploy] [error] [model.cpp:21] failed to create model: not supported (2)
I also encountered the same problem. Have you solved it? I encountered this problem while debugging the rotated_object_detection.cpp provided by the official.
