mmcv
mmcv copied to clipboard
open-mmlab
If I replace F.grid_sample with mmcv's bilinear_grid_sample，failed to export onnx to tensorrt
Checklist
- I have searched related issues but cannot get the expected help.
- I have read the FAQ documentation but cannot get the expected help.
2023-01-17 18:19:23,333 - mmdeploy - INFO - MSVC: 用于 x64 的 Microsoft (R) C/C++ 优化编译器 19.33.31629 版 2023-01-17 18:19:23,333 - mmdeploy - INFO - GCC: n/a 2023-01-17 18:19:23,333 - mmdeploy - INFO - PyTorch: 1.9.0+cu111 2023-01-17 18:19:23,333 - mmdeploy - INFO - PyTorch compiling details: PyTorch built with:
- C++ Version: 199711
- MSVC 192829337
- Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb)
- OpenMP 2019
- CPU capability usage: AVX2
- CUDA Runtime 11.1
- NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-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_37,code=compute_37
- CuDNN 8.0.5
- Magma 2.5.4
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=C:/w/b/windows/tmp_bin/sccache-cl.exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /w /bigobj -DUSE_PTHREADPOOL -openmp:experimental -IC:/w/b/windows/mkl/include -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DUSE_FBGEMM -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.0, 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,
2023-01-17 18:19:23,333 - mmdeploy - INFO - TorchVision: 0.10.0+cu111 2023-01-17 18:19:23,333 - mmdeploy - INFO - OpenCV: 4.6.0 2023-01-17 18:19:23,333 - mmdeploy - INFO - MMCV: 1.5.1 2023-01-17 18:19:23,333 - mmdeploy - INFO - MMCV Compiler: MSVC 192930137 2023-01-17 18:19:23,333 - mmdeploy - INFO - MMCV CUDA Compiler: 11.1 2023-01-17 18:19:23,333 - mmdeploy - INFO - MMDeploy: 0.12.0+c0e05b4 2023-01-17 18:19:23,333 - mmdeploy - INFO -
2023-01-17 18:19:23,333 - mmdeploy - INFO - Backend information 2023-01-17 18:19:25,797 - mmdeploy - INFO - tensorrt: 8.2.3.0 2023-01-17 18:19:25,798 - mmdeploy - INFO - tensorrt custom ops: Available 2023-01-17 18:19:26,177 - mmdeploy - INFO - ONNXRuntime: 1.8.1 2023-01-17 18:19:26,177 - mmdeploy - INFO - ONNXRuntime-gpu: None 2023-01-17 18:19:26,177 - mmdeploy - INFO - ONNXRuntime custom ops: Available 2023-01-17 18:19:26,291 - mmdeploy - INFO - pplnn: None 2023-01-17 18:19:26,599 - mmdeploy - INFO - ncnn: None 2023-01-17 18:19:26,778 - mmdeploy - INFO - snpe: None 2023-01-17 18:19:26,822 - mmdeploy - INFO - openvino: None 2023-01-17 18:19:26,906 - mmdeploy - INFO - torchscript: 1.9.0+cu111 2023-01-17 18:19:26,907 - mmdeploy - INFO - torchscript custom ops: NotAvailable 2023-01-17 18:19:27,027 - mmdeploy - INFO - rknn-toolkit: None 2023-01-17 18:19:27,027 - mmdeploy - INFO - rknn2-toolkit: None 2023-01-17 18:19:27,103 - mmdeploy - INFO - ascend: None 2023-01-17 18:19:27,176 - mmdeploy - INFO - coreml: None 2023-01-17 18:19:27,238 - mmdeploy - INFO - tvm: None 2023-01-17 18:19:27,238 - mmdeploy - INFO -
2023-01-17 18:19:27,238 - mmdeploy - INFO - Codebase information 2023-01-17 18:19:27,276 - mmdeploy - INFO - mmdet: None 2023-01-17 18:19:27,276 - mmdeploy - INFO - mmseg: None 2023-01-17 18:19:27,277 - mmdeploy - INFO - mmcls: 0.25.0 2023-01-17 18:19:27,277 - mmdeploy - INFO - mmocr: None 2023-01-17 18:19:27,277 - mmdeploy - INFO - mmedit: None 2023-01-17 18:19:27,277 - mmdeploy - INFO - mmdet3d: None 2023-01-17 18:19:27,277 - mmdeploy - INFO - mmpose: None 2023-01-17 18:19:27,277 - mmdeploy - INFO - mmrotate: None 2023-01-17 18:19:27,277 - mmdeploy - INFO - mmaction: None 2023-01-17 18:19:27,277 - mmdeploy - INFO - mmflow: 0.5.1
