Description
Checklist
- I have searched related issues but cannot get the expected help.
- 2. I have read the FAQ documentation but cannot get the expected help.
- 3. The bug has not been fixed in the latest version.
Describe the bug
Hi, I used mmdeploy to deploy detr, I can get onnx model and tensorrt model successfully, but when I used python demo/python/object_detection.py , it failed. The message is as fallow.
(openmmlab) jetson@Yahboom:~/mmdeploy$ python demo/python/object_detection.py cuda /home/jetson/mmdeploy/output/detr/ "/home/jetson/20.DL_pipeline/mmdeploy_test/images/20160720_233237.jpg"
[2023-03-14 20:08:09.814] [mmdeploy] [info] [model.cpp:35] [DirectoryModel] Load model: "/home/jetson/mmdeploy/output/detr/"
[2023-03-14 20:08:12.433] [mmdeploy] [warning] [trt_net.cpp:24] TRTNet: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
[2023-03-14 20:08:14.389] [mmdeploy] [error] [trt_net.cpp:28] TRTNet: 2: [pluginV2DynamicExtRunner.cpp::execute::115] Error Code 2: Internal Error (Assertion status == kSTATUS_SUCCESS failed. )
[2023-03-14 20:08:14.389] [mmdeploy] [error] [trt_net.cpp:75] TRT forward failed
terminate called after throwing an instance of 'system_error2::status_errormmdeploy::StatusDomain'
what(): unknown (6) @ /home/jetson/mmdeploy/csrc/mmdeploy/net/trt/trt_net.cpp:205
Aborted (core dumped)
Reproduction
python demo/python/object_detection.py cuda /home/jetson/mmdeploy/output/detr/ "/home/jetson/20.DL_pipeline/mmdeploy_test/images/20160720_233237.jpg"
Environment
2023-03-14 20:07:13,392 - mmdeploy - INFO - **********Environmental information**********
2023-03-14 20:07:20,235 - mmdeploy - INFO - sys.platform: linux
2023-03-14 20:07:20,236 - mmdeploy - INFO - Python: 3.6.15 | packaged by conda-forge | (default, Dec 3 2021, 19:12:04) [GCC 9.4.0]
2023-03-14 20:07:20,237 - mmdeploy - INFO - CUDA available: True
2023-03-14 20:07:20,237 - mmdeploy - INFO - GPU 0: Xavier
2023-03-14 20:07:20,237 - mmdeploy - INFO - CUDA_HOME: /usr/local/cuda-10.2
2023-03-14 20:07:20,237 - mmdeploy - INFO - NVCC: Build cuda_10.2_r440.TC440_70.29663091_0
2023-03-14 20:07:20,238 - mmdeploy - INFO - GCC: gcc (Ubuntu/Linaro 7.5.0-3ubuntu1~18.04) 7.5.0
2023-03-14 20:07:20,238 - mmdeploy - INFO - PyTorch: 1.10.0
2023-03-14 20:07:20,238 - mmdeploy - INFO - PyTorch compiling details: PyTorch built with:
- GCC 7.5
- C++ Version: 201402
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: NO AVX
- CUDA Runtime 10.2
- NVCC architecture flags: -gencode;arch=compute_53,code=sm_53;-gencode;arch=compute_62,code=sm_62;-gencode;arch=compute_72,code=sm_72
- CuDNN 8.2.1
- Built with CuDNN 8.0
- Build settings: BLAS_INFO=open, BUILD_TYPE=Release, CUDA_VERSION=10.2, CUDNN_VERSION=8.0.0, CXX_COMPILER=/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -DMISSING_ARM_VST1 -DMISSING_ARM_VLD1 -Wno-stringop-overflow, FORCE_FALLBACK_CUDA_MPI=1, LAPACK_INFO=open, TORCH_VERSION=1.10.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EIGEN_FOR_BLAS=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=OFF, USE_MKLDNN=OFF, USE_MPI=ON, USE_NCCL=0, USE_NNPACK=ON, USE_OPENMP=ON,
2023-03-14 20:07:20,238 - mmdeploy - INFO - TorchVision: 0.11.1
2023-03-14 20:07:20,239 - mmdeploy - INFO - OpenCV: 4.7.0
2023-03-14 20:07:20,239 - mmdeploy - INFO - MMCV: 1.4.0
2023-03-14 20:07:20,239 - mmdeploy - INFO - MMCV Compiler: GCC 7.5
2023-03-14 20:07:20,239 - mmdeploy - INFO - MMCV CUDA Compiler: 10.2
2023-03-14 20:07:20,240 - mmdeploy - INFO - MMDeploy: 0.13.0+f69c636
2023-03-14 20:07:20,240 - mmdeploy - INFO -
2023-03-14 20:07:20,240 - mmdeploy - INFO - **********Backend information**********
2023-03-14 20:07:20,580 - mmdeploy - INFO - tensorrt: 8.2.1.8
2023-03-14 20:07:20,581 - mmdeploy - INFO - tensorrt custom ops: Available
2023-03-14 20:07:20,774 - mmdeploy - INFO - ONNXRuntime: 1.10.0
2023-03-14 20:07:20,774 - mmdeploy - INFO - ONNXRuntime-gpu: None
2023-03-14 20:07:20,774 - mmdeploy - INFO - ONNXRuntime custom ops: NotAvailable
2023-03-14 20:07:20,778 - mmdeploy - INFO - pplnn: None
2023-03-14 20:07:20,786 - mmdeploy - INFO - ncnn: None
2023-03-14 20:07:20,794 - mmdeploy - INFO - snpe: None
2023-03-14 20:07:20,798 - mmdeploy - INFO - openvino: None
2023-03-14 20:07:20,805 - mmdeploy - INFO - torchscript: 1.10.0
2023-03-14 20:07:20,808 - mmdeploy - INFO - torchscript custom ops: NotAvailable
2023-03-14 20:07:20,981 - mmdeploy - INFO - rknn-toolkit: None
2023-03-14 20:07:20,981 - mmdeploy - INFO - rknn2-toolkit: None
2023-03-14 20:07:20,986 - mmdeploy - INFO - ascend: None
2023-03-14 20:07:20,991 - mmdeploy - INFO - coreml: None
2023-03-14 20:07:20,995 - mmdeploy - INFO - tvm: None
2023-03-14 20:07:20,995 - mmdeploy - INFO -
2023-03-14 20:07:20,996 - mmdeploy - INFO - **********Codebase information**********
2023-03-14 20:07:21,005 - mmdeploy - INFO - mmdet: 2.28.2
2023-03-14 20:07:21,005 - mmdeploy - INFO - mmseg: None
2023-03-14 20:07:21,005 - mmdeploy - INFO - mmcls: None
2023-03-14 20:07:21,005 - mmdeploy - INFO - mmocr: None
2023-03-14 20:07:21,005 - mmdeploy - INFO - mmedit: None
2023-03-14 20:07:21,005 - mmdeploy - INFO - mmdet3d: None
2023-03-14 20:07:21,006 - mmdeploy - INFO - mmpose: None
2023-03-14 20:07:21,006 - mmdeploy - INFO - mmrotate: None
2023-03-14 20:07:21,006 - mmdeploy - INFO - mmaction: NoneError traceback
No response