mmdeploy icon indicating copy to clipboard operation
mmdeploy copied to clipboard

Published 20 hours ago • verified publisher icon open-mmlab

Error Code 2: Internal Error (Assertion cublasStatus == CUBLAS_STATUS_SUCCESS failed. )

Open brilliant-soilder opened this issue 3 years ago • 3 comments

When I convert .pth to .engine model on the windows10 system. It successfully converted .onnx, but failed trt ,with an error occured as "Error Code 2: Internal Error (Assertion cublasStatus == CUBLAS_STATUS_SUCCESS failed. )"

Here lays the error info for help: (trt2) E:\mmdeploy\tools>python deploy.py E:\mmdeploy\configs\mmdet\instance-seg\instance-seg_tensorrt-fp16_dynamic-320x320-1344x1344_2.py E:\mmdetection-2.25.0\configs\mask_rcnn\mask_rcnn_x101_64x4d_fpn_mstrain-poly_3x_coco2.py E:\mmdetection-2.25.0\checkpoints\epoch_36.pth E:\mmdetection-2.25.0\demo\1\1_0050.bmp --work-dir E:\mmdeploy\work_dirs\640x256\30 --device cuda:0 --show --dump-info [2022-08-08 09:35:43.971] [mmdeploy] [info] [model.cpp:95] Register 'DirectoryModel' [2022-08-08 09:35:45.757] [mmdeploy] [info] [model.cpp:95] Register 'DirectoryModel' e:\mmdetection-2.25.0\mmdet\datasets\utils.py:66: UserWarning: "ImageToTensor" pipeline is replaced by "DefaultFormatBundle" for batch inference. It is recommended to manually replace it in the test data pipeline in your config file. warnings.warn( [2022-08-08 09:35:51.862] [mmdeploy] [info] [model.cpp:95] Register 'DirectoryModel' 2022-08-08 09:35:51,863 - mmdeploy - INFO - Start pipeline mmdeploy.apis.pytorch2onnx.torch2onnx in subprocess load checkpoint from local path: E:\mmdetection-2.25.0\checkpoints\epoch_36.pth e:\mmdetection-2.25.0\mmdet\datasets\utils.py:66: UserWarning: "ImageToTensor" pipeline is replaced by "DefaultFormatBundle" for batch inference. It is recommended to manually replace it in the test data pipeline in your config file. warnings.warn( 2022-08-08 09:35:57,871 - mmdeploy - WARNING - DeprecationWarning: get_onnx_config will be deprecated in the future. 2022-08-08 09:35:57,871 - mmdeploy - INFO - Export PyTorch model to ONNX: E:\mmdeploy\work_dirs\640x256\30\end2end.onnx. 2022-08-08 09:35:57,931 - mmdeploy - WARNING - Can not find torch._C._jit_pass_onnx_deduplicate_initializers, function rewrite will not be applied e:\mmdeploy\mmdeploy\core\optimizers\function_marker.py:158: TracerWarning: Converting a tensor to a Python integer might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! ys_shape = tuple(int(s) for s in ys.shape) e:\mmdetection-2.25.0\mmdet\models\dense_heads\anchor_head.py:123: UserWarning: DeprecationWarning: anchor_generator is deprecated, please use "prior_generator" instead warnings.warn('DeprecationWarning: anchor_generator is deprecated, ' e:\mmdetection-2.25.0\mmdet\core\anchor\anchor_generator.py:333: UserWarning: grid_anchors would be deprecated soon. Please use grid_priors warnings.warn('grid_anchors would be deprecated soon. ' e:\mmdetection-2.25.0\mmdet\core\anchor\anchor_generator.py:369: UserWarning: single_level_grid_anchors would be deprecated soon. Please use single_level_grid_priors warnings.warn( e:\mmdeploy\mmdeploy\codebase\mmdet\models\dense_heads\rpn_head.py:78: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! assert cls_score.size()[-2:] == bbox_pred.size()[-2:] e:\mmdeploy\mmdeploy\pytorch\functions\topk.py:56: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if k > size: e:\mmdeploy\mmdeploy\codebase\mmdet\core\bbox\delta_xywh_bbox_coder.py:39: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! assert pred_bboxes.size(0) == bboxes.size(0) e:\mmdeploy\mmdeploy\codebase\mmdet\core\bbox\delta_xywh_bbox_coder.py:41: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! assert pred_bboxes.size(1) == bboxes.size(1) e:\mmdeploy\mmdeploy\codebase\mmdet\core\post_processing\bbox_nms.py:259: TracerWarning: Converting a tensor to a Python integer might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! dets, labels = TRTBatchedNMSop.apply(boxes, scores, int(scores.shape[-1]), e:\mmdeploy\mmdeploy\mmcv\ops\nms.py:178: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! out_boxes = min(num_boxes, after_topk) F:\anaconda\anzhuangweizhi\envs\trt2\lib\site-packages\torch\onnx\symbolic_opset9.py:2603: UserWarning: Exporting aten::index operator of advanced indexing in opset 11 is achieved by combination of multiple ONNX operators, including Reshape, Transpose, Concat, and Gather. If indices include negative values, the exported graph will produce incorrect results. warnings.warn("Exporting aten::index operator of advanced indexing in opset " + 2022-08-08 09:36:03,756 - mmdeploy - INFO - Execute onnx optimize passes. 2022-08-08 09:36:04,894 - mmdeploy - INFO - Finish pipeline mmdeploy.apis.pytorch2onnx.torch2onnx [2022-08-08 09:36:07.174] [mmdeploy] [info] [model.cpp:95] Register 'DirectoryModel' 2022-08-08 09:36:07,171 - mmdeploy - INFO - Start pipeline mmdeploy.backend.tensorrt.onnx2tensorrt.onnx2tensorrt in subprocess 2022-08-08 09:36:08,167 - mmdeploy - INFO - Successfully loaded tensorrt plugins from e:\mmdeploy\mmdeploy\lib\mmdeploy_tensorrt_ops.dll [08/08/2022-09:36:08] [TRT] [I] [MemUsageChange] Init CUDA: CPU +323, GPU +0, now: CPU 4890, GPU 886 (MiB) [08/08/2022-09:36:08] [TRT] [I] [MemUsageSnapshot] Begin constructing builder kernel library: CPU 4920 MiB, GPU 886 MiB [08/08/2022-09:36:08] [TRT] [I] [MemUsageSnapshot] End constructing builder kernel library: CPU 5015 MiB, GPU 922 MiB [08/08/2022-09:36:09] [TRT] [W] onnx2trt_utils.cpp:366: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32. [08/08/2022-09:36:09] [TRT] [W] onnx2trt_utils.cpp:392: One or more weights outside the range of INT32 was clamped [08/08/2022-09:36:11] [TRT] [I] No importer registered for op: TRTBatchedNMS. Attempting to import as plugin. [08/08/2022-09:36:11] [TRT] [I] Searching for plugin: TRTBatchedNMS, plugin_version: 1, plugin_namespace: [08/08/2022-09:36:11] [TRT] [I] Successfully created plugin: TRTBatchedNMS [08/08/2022-09:36:11] [TRT] [I] No importer registered for op: MMCVMultiLevelRoiAlign. Attempting to import as plugin. [08/08/2022-09:36:11] [TRT] [I] Searching for plugin: MMCVMultiLevelRoiAlign, plugin_version: 1, plugin_namespace: [08/08/2022-09:36:11] [TRT] [I] Successfully created plugin: MMCVMultiLevelRoiAlign [08/08/2022-09:36:12] [TRT] [W] Tensor DataType is determined at build time for tensors not marked as input or output. [08/08/2022-09:36:13] [TRT] [I] No importer registered for op: TRTBatchedNMS. Attempting to import as plugin. [08/08/2022-09:36:13] [TRT] [I] Searching for plugin: TRTBatchedNMS, plugin_version: 1, plugin_namespace: [08/08/2022-09:36:13] [TRT] [I] Successfully created plugin: TRTBatchedNMS [08/08/2022-09:36:13] [TRT] [I] No importer registered for op: MMCVMultiLevelRoiAlign. Attempting to import as plugin. [08/08/2022-09:36:13] [TRT] [I] Searching for plugin: MMCVMultiLevelRoiAlign, plugin_version: 1, plugin_namespace: [08/08/2022-09:36:13] [TRT] [I] Successfully created plugin: MMCVMultiLevelRoiAlign [08/08/2022-09:36:13] [TRT] [W] Output type must be INT32 for shape outputs [08/08/2022-09:36:13] [TRT] [W] Output type must be INT32 for shape outputs [08/08/2022-09:36:14] [TRT] [I] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +180, GPU +70, now: CPU 5301, GPU 992 (MiB) [08/08/2022-09:36:14] [TRT] [I] [MemUsageChange] Init cuDNN: CPU +167, GPU +88, now: CPU 5468, GPU 1080 (MiB) [08/08/2022-09:36:14] [TRT] [I] Local timing cache in use. Profiling results in this builder pass will not be stored. [08/08/2022-09:37:14] [TRT] [I] Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output. [08/08/2022-09:41:07] [TRT] [E] 2: [ltWrapper.cpp::nvinfer1::rt::CublasLtWrapper::setupHeuristic::327] Error Code 2: Internal Error (Assertion cublasStatus == CUBLAS_STATUS_SUCCESS failed. ) Process Process-3: Traceback (most recent call last): File "F:\anaconda\anzhuangweizhi\envs\trt2\lib\multiprocessing\process.py", line 315, in _bootstrap self.run() File "F:\anaconda\anzhuangweizhi\envs\trt2\lib\multiprocessing\process.py", line 108, in run self._target(*self._args, **self._kwargs) File "e:\mmdeploy\mmdeploy\apis\core\pipeline_manager.py", line 107, in call ret = func(*args, **kwargs) File "e:\mmdeploy\mmdeploy\backend\tensorrt\onnx2tensorrt.py", line 79, in onnx2tensorrt from_onnx( File "e:\mmdeploy\mmdeploy\backend\tensorrt\utils.py", line 154, in from_onnx assert engine is not None, 'Failed to create TensorRT engine' AssertionError: Failed to create TensorRT engine 2022-08-08 09:41:08,084 - mmdeploy - ERROR - mmdeploy.backend.tensorrt.onnx2tensorrt.onnx2tensorrt with Call id: 1 failed. exit.

brilliant-soilder avatar Aug 08 '22 01:08 brilliant-soilder

(trt2) E:\mmdeploy\tools>python check_env.py 2022-08-08 09:42:29,467 - mmdeploy - INFO -

2022-08-08 09:42:29,467 - mmdeploy - INFO - Environmental information 'tail' 不是内部或外部命令，也不是可运行的程序 或批处理文件。 'gcc' 不是内部或外部命令，也不是可运行的程序 或批处理文件。 2022-08-08 09:42:32,010 - mmdeploy - INFO - sys.platform: win32 2022-08-08 09:42:32,010 - mmdeploy - INFO - Python: 3.9.12 (main, Apr 4 2022, 05:22:27) [MSC v.1916 64 bit (AMD64)] 2022-08-08 09:42:32,010 - mmdeploy - INFO - CUDA available: True 2022-08-08 09:42:32,010 - mmdeploy - INFO - GPU 0: GeForce GTX 1650 2022-08-08 09:42:32,010 - mmdeploy - INFO - CUDA_HOME: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.2 2022-08-08 09:42:32,010 - mmdeploy - INFO - NVCC: Not Available 2022-08-08 09:42:32,020 - mmdeploy - INFO - GCC: n/a 2022-08-08 09:42:32,020 - mmdeploy - INFO - PyTorch: 1.8.0 2022-08-08 09:42:32,020 - 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 v1.7.0 (Git Hash 7aed236906b1f7a05c0917e5257a1af05e9ff683)
  • OpenMP 2019
  • CPU capability usage: AVX2
  • CUDA Runtime 10.2
  • 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_37,code=compute_37
  • CuDNN 7.6.5
  • Magma 2.5.4
  • Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=10.2, CUDNN_VERSION=7.6.5, CXX_COMPILER=C:/w/b/windows/tmp_bin/sccache-cl.exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /w /bigobj -DUSE_PTHREADPOOL -openmp:experimental -DNDEBUG -DUSE_FBGEMM -DUSE_XNNPACK, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.8.0, 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,

2022-08-08 09:42:32,020 - mmdeploy - INFO - TorchVision: 0.9.0 2022-08-08 09:42:32,020 - mmdeploy - INFO - OpenCV: 4.6.0 2022-08-08 09:42:32,020 - mmdeploy - INFO - MMCV: 1.4.0 2022-08-08 09:42:32,020 - mmdeploy - INFO - MMCV Compiler: MSVC 192930145 2022-08-08 09:42:32,020 - mmdeploy - INFO - MMCV CUDA Compiler: 10.2 2022-08-08 09:42:32,020 - mmdeploy - INFO - MMDeploy: 0.6.0+a15365e 2022-08-08 09:42:32,020 - mmdeploy - INFO -

2022-08-08 09:42:32,020 - mmdeploy - INFO - Backend information 2022-08-08 09:42:33,235 - mmdeploy - INFO - onnxruntime: 1.8.1 ops_is_avaliable : True 2022-08-08 09:42:33,263 - mmdeploy - INFO - tensorrt: 8.2.3.0 ops_is_avaliable : True 2022-08-08 09:42:33,295 - mmdeploy - INFO - ncnn: None ops_is_avaliable : False 2022-08-08 09:42:33,295 - mmdeploy - INFO - pplnn_is_avaliable: False 2022-08-08 09:42:33,295 - mmdeploy - INFO - openvino_is_avaliable: False 2022-08-08 09:42:33,343 - mmdeploy - INFO - snpe_is_available: False 2022-08-08 09:42:33,343 - mmdeploy - INFO -

2022-08-08 09:42:33,345 - mmdeploy - INFO - Codebase information 2022-08-08 09:42:33,353 - mmdeploy - INFO - mmdet: 2.25.0 2022-08-08 09:42:33,353 - mmdeploy - INFO - mmseg: None 2022-08-08 09:42:33,353 - mmdeploy - INFO - mmcls: None 2022-08-08 09:42:33,353 - mmdeploy - INFO - mmocr: None 2022-08-08 09:42:33,353 - mmdeploy - INFO - mmedit: None 2022-08-08 09:42:33,363 - mmdeploy - INFO - mmdet3d: None 2022-08-08 09:42:33,363 - mmdeploy - INFO - mmpose: None 2022-08-08 09:42:33,365 - mmdeploy - INFO - mmrotate: None

brilliant-soilder avatar Aug 08 '22 01:08 brilliant-soilder

Can you try to set config according to https://github.com/open-mmlab/mmdeploy/issues/261

irexyc avatar Aug 08 '22 03:08 irexyc

Can you try to set config according to #261

Success. It works with your suggestion. But some guys runs successfully whther with this option <<"Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output">> and shows no error . SO why is this happened to mine, is it a reason because mmdeploy's version?

brilliant-soilder avatar Aug 08 '22 03:08 brilliant-soilder

The problem is due to the cuda version. If you use cuda11+, you won't meet (Assertion cublasStatus == CUBLAS_STATUS_SUCCESS failed. )

irexyc avatar Aug 08 '22 08:08 irexyc

The problem is due to the cuda version. If you use cuda11+, you won't meet (Assertion cublasStatus == CUBLAS_STATUS_SUCCESS failed. )

What can I do if I am using cuda11+? Would you suggest to degrade it? This is working fine when I am using mmdeploy for detection/config/swin and detectoin/config/yolox but stucked in pvt (used int8 config for deployment) Here is my error message along with my environment: [11/22/2022-14:23:17] [TRT] [W] If this is not the desired behavior, please modify the weights or retrain with regularization to reduce the magnitude of the weights. [11/22/2022-14:23:17] [TRT] [E] 2: [ltWrapper.cpp::setupHeuristic::349] Error Code 2: Internal Error (Assertion cublasStatus == CUBLAS_STATUS_SUCCESS failed. ) Process Process-4: Traceback (most recent call last): File "/home/dee08770/anaconda3/envs/mmdeploy/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/dee08770/anaconda3/envs/mmdeploy/lib/python3.8/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/dee08770/anaconda3/envs/mmdeploy/lib/python3.8/site-packages/mmdeploy/apis/core/pipeline_manager.py", line 107, in call ret = func(*args, **kwargs) File "/home/dee08770/anaconda3/envs/mmdeploy/lib/python3.8/site-packages/mmdeploy/backend/tensorrt/onnx2tensorrt.py", line 79, in onnx2tensorrt from_onnx( File "/home/dee08770/anaconda3/envs/mmdeploy/lib/python3.8/site-packages/mmdeploy/backend/tensorrt/utils.py", line 215, in from_onnx assert engine is not None, 'Failed to create TensorRT engine' AssertionError: Failed to create TensorRT engine 2022-11-22 14:23:18,895 - mmdeploy - ERROR - mmdeploy.backend.tensorrt.onnx2tensorrt.onnx2tensorrt with Call id: 2 failed. exit. (mmdeploy) dee08770@dione:~/mmdetection$ cd .. (mmdeploy) dee08770@dione:~$ cd mmdeploy (mmdeploy) dee08770@dione:~/mmdeploy$ cd tools/ (mmdeploy) dee08770@dione:~/mmdeploy/tools$ python check_env.py 2022-11-22 14:25:21,319 - mmdeploy - INFO -

2022-11-22 14:25:21,319 - mmdeploy - INFO - Environmental information 2022-11-22 14:25:22,176 - mmdeploy - INFO - sys.platform: linux 2022-11-22 14:25:22,176 - mmdeploy - INFO - Python: 3.8.13 (default, Mar 28 2022, 11:38:47) [GCC 7.5.0] 2022-11-22 14:25:22,176 - mmdeploy - INFO - CUDA available: True 2022-11-22 14:25:22,176 - mmdeploy - INFO - GPU 0: NVIDIA GeForce RTX 2060 2022-11-22 14:25:22,176 - mmdeploy - INFO - CUDA_HOME: /home/dee08770/anaconda3/envs/mmdeploy 2022-11-22 14:25:22,176 - mmdeploy - INFO - NVCC: Cuda compilation tools, release 11.3, V11.3.122 2022-11-22 14:25:22,176 - mmdeploy - INFO - GCC: gcc (Debian 10.2.1-6) 10.2.1 20210110 2022-11-22 14:25:22,176 - mmdeploy - INFO - PyTorch: 1.12.1 2022-11-22 14:25:22,176 - mmdeploy - INFO - PyTorch compiling details: PyTorch built with:

  • GCC 9.3
  • C++ Version: 201402
  • Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications
  • Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
  • OpenMP 201511 (a.k.a. OpenMP 4.5)
  • LAPACK is enabled (usually provided by MKL)
  • NNPACK is enabled
  • CPU capability usage: AVX2
  • CUDA Runtime 11.3
  • 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 8.3.2 (built against CUDA 11.5)
  • Magma 2.5.2
  • Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -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-unused-parameter -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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,

2022-11-22 14:25:22,176 - mmdeploy - INFO - TorchVision: 0.13.1 2022-11-22 14:25:22,176 - mmdeploy - INFO - OpenCV: 4.6.0 2022-11-22 14:25:22,176 - mmdeploy - INFO - MMCV: 1.6.2 2022-11-22 14:25:22,176 - mmdeploy - INFO - MMCV Compiler: GCC 9.3 2022-11-22 14:25:22,176 - mmdeploy - INFO - MMCV CUDA Compiler: 11.3 2022-11-22 14:25:22,176 - mmdeploy - INFO - MMDeploy: 0.9.0+917643f 2022-11-22 14:25:22,176 - mmdeploy - INFO -

2022-11-22 14:25:22,176 - mmdeploy - INFO - Backend information 2022-11-22 14:25:23,248 - mmdeploy - INFO - onnxruntime: None ops_is_avaliable : False 2022-11-22 14:25:23,272 - mmdeploy - INFO - tensorrt: 8.4.1.5 ops_is_avaliable : True 2022-11-22 14:25:23,378 - mmdeploy - INFO - ncnn: None ops_is_avaliable : False 2022-11-22 14:25:23,412 - mmdeploy - INFO - pplnn_is_avaliable: False 2022-11-22 14:25:23,460 - mmdeploy - INFO - openvino_is_avaliable: False 2022-11-22 14:25:23,567 - mmdeploy - INFO - snpe_is_available: False 2022-11-22 14:25:23,611 - mmdeploy - INFO - ascend_is_available: False 2022-11-22 14:25:23,641 - mmdeploy - INFO - coreml_is_available: False 2022-11-22 14:25:23,641 - mmdeploy - INFO -

dpakprajul avatar Nov 22 '22 13:11 dpakprajul