mmdeploy icon indicating copy to clipboard operation
mmdeploy copied to clipboard

Published 20 hours ago • verified publisher icon open-mmlab

[Bug] - mmdeploy - ERROR - scope_name should be a string, but got None

Open xuexisuanfa opened this issue 1 year ago • 9 comments

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

在mmrotate中，训练rotated-faster-rcnn得到epoch_12.pth文件，然后按照官网教程https://mmdeploy.readthedocs.io/zh_CN/latest/get_started.html 中的模型转换，并收集好相关文件作出相应调整，但是运行出错了，结果如下（本次使用的是dev-1.x）：

(mmdeploy1x) oem@li:~/mmdeploy-dev-1.x$ python mmdeploy/tools/deploy.py rotatedfasterrcnn/rotated-detection_tensorrt_dynamic-320x320-1024x1024.py rotatedfasterrcnn/rotated_faster_rcnn_r50_fpn_1x_dota_le90.py rotatedfasterrcnn/epoch_12.pth rotatedfasterrcnn/demo.png --work-dir mmdeploy_model/rotatedfasterrcnn --device cuda --dump-info 03/15 09:29:17 - mmengine - WARNING - Failed to search registry with scope "mmrotate" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmrotate" is a correct scope, or whether the registry is initialized. 03/15 09:29:17 - mmengine - WARNING - Failed to search registry with scope "mmrotate" in the "mmrotate_tasks" registry tree. As a workaround, the current "mmrotate_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmrotate" is a correct scope, or whether the registry is initialized. 03/15 09:29:17 - mmengine - WARNING - Failed to search registry with scope "mmrotate" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmrotate" is a correct scope, or whether the registry is initialized. Traceback (most recent call last): File "/home/oem/anaconda3/envs/mmdeploy1x/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg obj = obj_cls(**args) # type: ignore File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/codebase/mmrotate/deploy/rotated_detection.py", line 156, in init super().init(model_cfg, deploy_cfg, device, experiment_name) File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/codebase/base/task.py", line 53, in init self.scope = DefaultScope.get_instance( File "/home/oem/anaconda3/envs/mmdeploy1x/lib/python3.8/site-packages/mmengine/utils/manager.py", line 109, in get_instance instance = cls(name=name, **kwargs) # type: ignore File "/home/oem/anaconda3/envs/mmdeploy1x/lib/python3.8/site-packages/mmengine/registry/default_scope.py", line 35, in init assert isinstance( AssertionError: scope_name should be a string, but got None

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "mmdeploy/tools/deploy.py", line 335, in main() File "mmdeploy/tools/deploy.py", line 129, in main export2SDK( File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 347, in export2SDK deploy_info = get_deploy(deploy_cfg, model_cfg, work_dir, device) File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 262, in get_deploy _, customs = get_model_name_customs( File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 61, in get_model_name_customs task_processor = build_task_processor( File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/apis/utils/utils.py", line 48, in build_task_processor return codebase.build_task_processor(model_cfg, deploy_cfg, device) File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/codebase/base/mmcodebase.py", line 45, in build_task_processor return cls.task_registry.build( File "/home/oem/anaconda3/envs/mmdeploy1x/lib/python3.8/site-packages/mmengine/registry/registry.py", line 548, in build return self.build_func(cfg, *args, **kwargs, registry=self) File "/home/oem/anaconda3/envs/mmdeploy1x/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 135, in build_from_cfg raise type(e)( AssertionError: class RotatedDetection in mmdeploy/codebase/mmrotate/deploy/rotated_detection.py: scope_name should be a string, but got None

Reproduction

python mmdeploy/tools/deploy.py rotatedfasterrcnn/rotated-detection_tensorrt_dynamic-320x320-1024x1024.py rotatedfasterrcnn/rotated_faster_rcnn_r50_fpn_1x_dota_le90.py rotatedfasterrcnn/epoch_12.pth rotatedfasterrcnn/demo.png --work-dir mmdeploy_model/rotatedfasterrcnn --device cuda --dump-info

请注意收集好相关文件

r

Environment

无

Error traceback

No response

xuexisuanfa avatar Mar 10 '23 02:03 xuexisuanfa

Did you add the directory of TensorRT to your .bashrc file ?

mofibo avatar Mar 10 '23 11:03 mofibo

Did you add the directory of TensorRT to your .bashrc file ? Yes,i did. I use the pth file of mmdetection to convert is successful, but to convert the pth file of mmrotate is failed.

xuexisuanfa avatar Mar 13 '23 01:03 xuexisuanfa

same problem...

HwanWoongLee avatar Mar 14 '23 04:03 HwanWoongLee

rotated faster rcnn has been supported in dev-1.x branch

grimoire avatar Mar 14 '23 06:03 grimoire

rotated faster rcnn has been supported in dev-1.x branch

能说说虚拟环境得各个库得版本吗 mmrotate mmcv mmdet mmcv mmcv-full 等，我发现出现了版本矛盾问题，调了很久。

xuexisuanfa avatar Mar 14 '23 08:03 xuexisuanfa

rotated faster rcnn has been supported in dev-1.x branch 您好， 使用 dev-1.x 出了新错误：

(mmdeploy1x) oem@li:~/mmdeploy-dev-1.x$ python mmdeploy/tools/deploy.py rotatedfasterrcnn/rotated-detection_tensorrt_dynamic-320x320-1024x1024.py rotatedfasterrcnn/rotated_faster_rcnn_r50_fpn_1x_dota_le90.py rotatedfasterrcnn/epoch_12.pth rotatedfasterrcnn/demo.png --work-dir mmdeploy_model/rotatedfasterrcnn --device cuda --dump-info 03/15 09:29:17 - mmengine - WARNING - Failed to search registry with scope "mmrotate" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmrotate" is a correct scope, or whether the registry is initialized. 03/15 09:29:17 - mmengine - WARNING - Failed to search registry with scope "mmrotate" in the "mmrotate_tasks" registry tree. As a workaround, the current "mmrotate_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmrotate" is a correct scope, or whether the registry is initialized. 03/15 09:29:17 - mmengine - WARNING - Failed to search registry with scope "mmrotate" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmrotate" is a correct scope, or whether the registry is initialized. Traceback (most recent call last): File "/home/oem/anaconda3/envs/mmdeploy1x/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg obj = obj_cls(**args) # type: ignore File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/codebase/mmrotate/deploy/rotated_detection.py", line 156, in init super().init(model_cfg, deploy_cfg, device, experiment_name) File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/codebase/base/task.py", line 53, in init self.scope = DefaultScope.get_instance( File "/home/oem/anaconda3/envs/mmdeploy1x/lib/python3.8/site-packages/mmengine/utils/manager.py", line 109, in get_instance instance = cls(name=name, **kwargs) # type: ignore File "/home/oem/anaconda3/envs/mmdeploy1x/lib/python3.8/site-packages/mmengine/registry/default_scope.py", line 35, in init assert isinstance( AssertionError: scope_name should be a string, but got None

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "mmdeploy/tools/deploy.py", line 335, in main() File "mmdeploy/tools/deploy.py", line 129, in main export2SDK( File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 347, in export2SDK deploy_info = get_deploy(deploy_cfg, model_cfg, work_dir, device) File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 262, in get_deploy _, customs = get_model_name_customs( File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 61, in get_model_name_customs task_processor = build_task_processor( File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/apis/utils/utils.py", line 48, in build_task_processor return codebase.build_task_processor(model_cfg, deploy_cfg, device) File "/home/oem/mmdeploy-dev-1.x/mmdeploy/mmdeploy/codebase/base/mmcodebase.py", line 45, in build_task_processor return cls.task_registry.build( File "/home/oem/anaconda3/envs/mmdeploy1x/lib/python3.8/site-packages/mmengine/registry/registry.py", line 548, in build return self.build_func(cfg, *args, **kwargs, registry=self) File "/home/oem/anaconda3/envs/mmdeploy1x/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 135, in build_from_cfg raise type(e)( AssertionError: class RotatedDetection in mmdeploy/codebase/mmrotate/deploy/rotated_detection.py: scope_name should be a string, but got None

xuexisuanfa avatar Mar 15 '23 01:03 xuexisuanfa

Please post the result of python tools/check_env.py

FYI, I can successfully deploy rotated-faster-rcnn model by the following command:

python tools/deploy.py \
    configs/mmrotate/rotated-detection_tensorrt_dynamic-320x320-1024x1024.py
    /data1/checkpoint/mmrotate/rotated-faster-rcnn-le90_r50_fpn_1x_dota.py \
    /data1/checkpoint/mmrotate/rotated_faster_rcnn_r50_fpn_1x_dota_le90-0393aa5c.pth \
    ../mmrotate/demo/demo.jpg \
    --dump-info \
    --work-dir  /data1/mmdeploy_models/mmrotate/faster-rcnn/tensorrt \
    --device cuda

The following is my env:

03/20 12:56:59 - mmengine - INFO - 

03/20 12:56:59 - mmengine - INFO - **********Environmental information**********
03/20 12:56:59 - mmengine - INFO - sys.platform: linux
03/20 12:56:59 - mmengine - INFO - Python: 3.8.15 (default, Nov 24 2022, 15:19:38) [GCC 11.2.0]
03/20 12:56:59 - mmengine - INFO - CUDA available: True
03/20 12:56:59 - mmengine - INFO - numpy_random_seed: 2147483648
03/20 12:56:59 - mmengine - INFO - GPU 0: GeForce GTX 1660 SUPER
03/20 12:56:59 - mmengine - INFO - CUDA_HOME: /usr/local/cuda
03/20 12:56:59 - mmengine - INFO - NVCC: Cuda compilation tools, release 11.1, V11.1.74
03/20 12:56:59 - mmengine - INFO - GCC: gcc (Ubuntu 7.5.0-3ubuntu1~16.04) 7.5.0
03/20 12:56:59 - mmengine - INFO - PyTorch: 1.10.0+cu111
03/20 12:56:59 - mmengine - INFO - PyTorch compiling details: PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.1
  - 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_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
  - CuDNN 8.0.5
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -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-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 -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.10.0, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON, 

03/20 12:56:59 - mmengine - INFO - TorchVision: 0.11.0+cu111
03/20 12:56:59 - mmengine - INFO - OpenCV: 4.6.0
03/20 12:56:59 - mmengine - INFO - MMEngine: 0.6.0
03/20 12:56:59 - mmengine - INFO - MMCV: 2.0.0rc4
03/20 12:56:59 - mmengine - INFO - MMCV Compiler: GCC 7.3
03/20 12:56:59 - mmengine - INFO - MMCV CUDA Compiler: 11.1
03/20 12:56:59 - mmengine - INFO - MMDeploy: 1.0.0rc3+754c080
03/20 12:56:59 - mmengine - INFO - 

03/20 12:56:59 - mmengine - INFO - **********Backend information**********
03/20 12:56:59 - mmengine - INFO - tensorrt:    8.2.3.0
03/20 12:56:59 - mmengine - INFO - tensorrt custom ops: Available
03/20 12:56:59 - mmengine - INFO - ONNXRuntime: 1.8.1
03/20 12:56:59 - mmengine - INFO - ONNXRuntime-gpu:     None
03/20 12:56:59 - mmengine - INFO - ONNXRuntime custom ops:      Available
03/20 12:56:59 - mmengine - INFO - pplnn:       None
03/20 12:56:59 - mmengine - INFO - ncnn:        None
03/20 12:56:59 - mmengine - INFO - snpe:        None
03/20 12:56:59 - mmengine - INFO - openvino:    None
03/20 12:56:59 - mmengine - INFO - torchscript: 1.10.0+cu111
03/20 12:56:59 - mmengine - INFO - torchscript custom ops:      NotAvailable
03/20 12:56:59 - mmengine - INFO - rknn-toolkit:        None
03/20 12:56:59 - mmengine - INFO - rknn-toolkit2:       None
03/20 12:56:59 - mmengine - INFO - ascend:      None
03/20 12:56:59 - mmengine - INFO - coreml:      None
03/20 12:56:59 - mmengine - INFO - tvm: None
03/20 12:56:59 - mmengine - INFO - vacc:        None
03/20 12:56:59 - mmengine - INFO - 

03/20 12:56:59 - mmengine - INFO - **********Codebase information**********
03/20 12:56:59 - mmengine - INFO - mmdet:       3.0.0rc5
03/20 12:56:59 - mmengine - INFO - mmseg:       1.0.0rc5
03/20 12:56:59 - mmengine - INFO - mmcls:       1.0.0rc5
03/20 12:56:59 - mmengine - INFO - mmocr:       None
03/20 12:56:59 - mmengine - INFO - mmedit:      1.0.0rc6
03/20 12:56:59 - mmengine - INFO - mmdet3d:     None
03/20 12:56:59 - mmengine - INFO - mmpose:      1.0.0rc0
03/20 12:56:59 - mmengine - INFO - mmrotate:    1.0.0rc1
03/20 12:56:59 - mmengine - INFO - mmaction:    None
03/20 12:56:59 - mmengine - INFO - mmrazor:     None

lvhan028 avatar Mar 20 '23 05:03 lvhan028

Please post the result of python tools/check_env.py

FYI, I can successfully deploy rotated-faster-rcnn model by the following command:

python tools/deploy.py \
    configs/mmrotate/rotated-detection_tensorrt_dynamic-320x320-1024x1024.py
    /data1/checkpoint/mmrotate/rotated-faster-rcnn-le90_r50_fpn_1x_dota.py \
    /data1/checkpoint/mmrotate/rotated_faster_rcnn_r50_fpn_1x_dota_le90-0393aa5c.pth \
    ../mmrotate/demo/demo.jpg \
    --dump-info \
    --work-dir  /data1/mmdeploy_models/mmrotate/faster-rcnn/tensorrt \
    --device cuda

The following is my env:

03/20 12:56:59 - mmengine - INFO - 

03/20 12:56:59 - mmengine - INFO - **********Environmental information**********
03/20 12:56:59 - mmengine - INFO - sys.platform: linux
03/20 12:56:59 - mmengine - INFO - Python: 3.8.15 (default, Nov 24 2022, 15:19:38) [GCC 11.2.0]
03/20 12:56:59 - mmengine - INFO - CUDA available: True
03/20 12:56:59 - mmengine - INFO - numpy_random_seed: 2147483648
03/20 12:56:59 - mmengine - INFO - GPU 0: GeForce GTX 1660 SUPER
03/20 12:56:59 - mmengine - INFO - CUDA_HOME: /usr/local/cuda
03/20 12:56:59 - mmengine - INFO - NVCC: Cuda compilation tools, release 11.1, V11.1.74
03/20 12:56:59 - mmengine - INFO - GCC: gcc (Ubuntu 7.5.0-3ubuntu1~16.04) 7.5.0
03/20 12:56:59 - mmengine - INFO - PyTorch: 1.10.0+cu111
03/20 12:56:59 - mmengine - INFO - PyTorch compiling details: PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.1
  - 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_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
  - CuDNN 8.0.5
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -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-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 -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.10.0, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON, 

03/20 12:56:59 - mmengine - INFO - TorchVision: 0.11.0+cu111
03/20 12:56:59 - mmengine - INFO - OpenCV: 4.6.0
03/20 12:56:59 - mmengine - INFO - MMEngine: 0.6.0
03/20 12:56:59 - mmengine - INFO - MMCV: 2.0.0rc4
03/20 12:56:59 - mmengine - INFO - MMCV Compiler: GCC 7.3
03/20 12:56:59 - mmengine - INFO - MMCV CUDA Compiler: 11.1
03/20 12:56:59 - mmengine - INFO - MMDeploy: 1.0.0rc3+754c080
03/20 12:56:59 - mmengine - INFO - 

03/20 12:56:59 - mmengine - INFO - **********Backend information**********
03/20 12:56:59 - mmengine - INFO - tensorrt:    8.2.3.0
03/20 12:56:59 - mmengine - INFO - tensorrt custom ops: Available
03/20 12:56:59 - mmengine - INFO - ONNXRuntime: 1.8.1
03/20 12:56:59 - mmengine - INFO - ONNXRuntime-gpu:     None
03/20 12:56:59 - mmengine - INFO - ONNXRuntime custom ops:      Available
03/20 12:56:59 - mmengine - INFO - pplnn:       None
03/20 12:56:59 - mmengine - INFO - ncnn:        None
03/20 12:56:59 - mmengine - INFO - snpe:        None
03/20 12:56:59 - mmengine - INFO - openvino:    None
03/20 12:56:59 - mmengine - INFO - torchscript: 1.10.0+cu111
03/20 12:56:59 - mmengine - INFO - torchscript custom ops:      NotAvailable
03/20 12:56:59 - mmengine - INFO - rknn-toolkit:        None
03/20 12:56:59 - mmengine - INFO - rknn-toolkit2:       None
03/20 12:56:59 - mmengine - INFO - ascend:      None
03/20 12:56:59 - mmengine - INFO - coreml:      None
03/20 12:56:59 - mmengine - INFO - tvm: None
03/20 12:56:59 - mmengine - INFO - vacc:        None
03/20 12:56:59 - mmengine - INFO - 

03/20 12:56:59 - mmengine - INFO - **********Codebase information**********
03/20 12:56:59 - mmengine - INFO - mmdet:       3.0.0rc5
03/20 12:56:59 - mmengine - INFO - mmseg:       1.0.0rc5
03/20 12:56:59 - mmengine - INFO - mmcls:       1.0.0rc5
03/20 12:56:59 - mmengine - INFO - mmocr:       None
03/20 12:56:59 - mmengine - INFO - mmedit:      1.0.0rc6
03/20 12:56:59 - mmengine - INFO - mmdet3d:     None
03/20 12:56:59 - mmengine - INFO - mmpose:      1.0.0rc0
03/20 12:56:59 - mmengine - INFO - mmrotate:    1.0.0rc1
03/20 12:56:59 - mmengine - INFO - mmaction:    None
03/20 12:56:59 - mmengine - INFO - mmrazor:     None

(mmdeploy1x) oem@li:~/mmdeploy-dev-1.x/mmdeploy$ python tools/check_env.py 03/24 08:35:52 - mmengine - INFO -

03/24 08:35:52 - mmengine - INFO - Environmental information 03/24 08:35:53 - mmengine - INFO - sys.platform: linux 03/24 08:35:53 - mmengine - INFO - Python: 3.8.13 (default, Mar 28 2022, 11:38:47) [GCC 7.5.0] 03/24 08:35:53 - mmengine - INFO - CUDA available: True 03/24 08:35:53 - mmengine - INFO - numpy_random_seed: 2147483648 03/24 08:35:53 - mmengine - INFO - GPU 0: NVIDIA GeForce GTX 1650 03/24 08:35:53 - mmengine - INFO - CUDA_HOME: /usr/local/cuda-10.2 03/24 08:35:53 - mmengine - INFO - NVCC: Cuda compilation tools, release 10.2, V10.2.8 03/24 08:35:53 - mmengine - INFO - GCC: gcc (Ubuntu 8.4.0-3ubuntu2) 8.4.0 03/24 08:35:53 - mmengine - INFO - PyTorch: 1.10.1+cu102 03/24 08:35:53 - mmengine - INFO - PyTorch compiling details: PyTorch built with:

  • GCC 7.3
  • C++ Version: 201402
  • Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  • Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
  • OpenMP 201511 (a.k.a. OpenMP 4.5)
  • LAPACK is enabled (usually provided by MKL)
  • NNPACK is enabled
  • 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_70,code=sm_70
  • CuDNN 7.6.5
  • Magma 2.5.2
  • Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=10.2, CUDNN_VERSION=7.6.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -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-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 -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.10.1, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON,

03/24 08:35:53 - mmengine - INFO - TorchVision: 0.11.2+cu102 03/24 08:35:53 - mmengine - INFO - OpenCV: 4.5.4 03/24 08:35:53 - mmengine - INFO - MMEngine: 0.5.0 03/24 08:35:53 - mmengine - INFO - MMCV: 2.0.0rc3 03/24 08:35:53 - mmengine - INFO - MMCV Compiler: GCC 7.3 03/24 08:35:53 - mmengine - INFO - MMCV CUDA Compiler: 10.2 03/24 08:35:53 - mmengine - INFO - MMDeploy: 1.0.0rc3+637958a 03/24 08:35:53 - mmengine - INFO -

03/24 08:35:53 - mmengine - INFO - Backend information 03/24 08:35:53 - mmengine - INFO - tensorrt: 8.4.1.5 03/24 08:35:53 - mmengine - INFO - tensorrt custom ops: Available 03/24 08:35:53 - mmengine - INFO - ONNXRuntime: 1.8.1 03/24 08:35:53 - mmengine - INFO - ONNXRuntime-gpu: None 03/24 08:35:53 - mmengine - INFO - ONNXRuntime custom ops: NotAvailable 03/24 08:35:53 - mmengine - INFO - pplnn: None 03/24 08:35:53 - mmengine - INFO - ncnn: None 03/24 08:35:53 - mmengine - INFO - snpe: None 03/24 08:35:53 - mmengine - INFO - openvino: None 03/24 08:35:53 - mmengine - INFO - torchscript: 1.10.1+cu102 03/24 08:35:53 - mmengine - INFO - torchscript custom ops: NotAvailable 03/24 08:35:53 - mmengine - INFO - rknn-toolkit: None 03/24 08:35:53 - mmengine - INFO - rknn-toolkit2: None 03/24 08:35:53 - mmengine - INFO - ascend: None 03/24 08:35:53 - mmengine - INFO - coreml: None 03/24 08:35:53 - mmengine - INFO - tvm: None 03/24 08:35:53 - mmengine - INFO - vacc: None 03/24 08:35:53 - mmengine - INFO -

03/24 08:35:53 - mmengine - INFO - Codebase information 03/24 08:35:53 - mmengine - INFO - mmdet: 3.0.0rc4 03/24 08:35:53 - mmengine - INFO - mmseg: None 03/24 08:35:53 - mmengine - INFO - mmcls: None 03/24 08:35:53 - mmengine - INFO - mmocr: None 03/24 08:35:53 - mmengine - INFO - mmedit: None 03/24 08:35:53 - mmengine - INFO - mmdet3d: None 03/24 08:35:53 - mmengine - INFO - mmpose: None 03/24 08:35:53 - mmengine - INFO - mmrotate: 1.0.0rc0 03/24 08:35:53 - mmengine - INFO - mmaction: None

以上是我的环境，cuda 只能装10.2， 但是还是会报错

xuexisuanfa avatar Mar 24 '23 00:03 xuexisuanfa

python tools/check_env.py 09/18 22:14:54 - mmengine - INFO -

09/18 22:14:54 - mmengine - INFO - Environmental information 09/18 22:14:55 - mmengine - INFO - sys.platform: linux 09/18 22:14:55 - mmengine - INFO - Python: 3.7.16 (default, Jan 17 2023, 22:20:44) [GCC 11.2.0] 09/18 22:14:55 - mmengine - INFO - CUDA available: True 09/18 22:14:55 - mmengine - INFO - numpy_random_seed: 2147483648 09/18 22:14:55 - mmengine - INFO - GPU 0,1,2,3,4,5,6,7: NVIDIA RTX A6000 09/18 22:14:55 - mmengine - INFO - CUDA_HOME: /usr/local/cuda/ 09/18 22:14:55 - mmengine - INFO - NVCC: Cuda compilation tools, release 11.3, V11.3.58 09/18 22:14:55 - mmengine - INFO - GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0 09/18 22:14:55 - mmengine - INFO - PyTorch: 1.8.0 09/18 22:14:55 - mmengine - INFO - PyTorch compiling details: PyTorch built with:

  • GCC 7.3
  • 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 v1.7.0 (Git Hash 7aed236906b1f7a05c0917e5257a1af05e9ff683)
  • OpenMP 201511 (a.k.a. OpenMP 4.5)
  • NNPACK is enabled
  • 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 2.5.2
  • Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -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 -Wno-stringop-overflow, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON,

09/18 22:14:55 - mmengine - INFO - TorchVision: 0.9.0 09/18 22:14:55 - mmengine - INFO - OpenCV: 4.8.0 09/18 22:14:55 - mmengine - INFO - MMEngine: 0.8.4 09/18 22:14:55 - mmengine - INFO - MMCV: 2.0.0 09/18 22:14:55 - mmengine - INFO - MMCV Compiler: GCC 9.4 09/18 22:14:55 - mmengine - INFO - MMCV CUDA Compiler: 11.3 09/18 22:14:55 - mmengine - INFO - MMDeploy: 1.2.0+bb031c6 09/18 22:14:55 - mmengine - INFO -

09/18 22:14:55 - mmengine - INFO - Backend information 09/18 22:14:55 - mmengine - INFO - tensorrt: 8.2.3.0 09/18 22:14:55 - mmengine - INFO - tensorrt custom ops: Available 09/18 22:14:55 - mmengine - INFO - ONNXRuntime: 1.8.1 09/18 22:14:55 - mmengine - INFO - ONNXRuntime-gpu: None 09/18 22:14:55 - mmengine - INFO - ONNXRuntime custom ops: Available 09/18 22:14:55 - mmengine - INFO - pplnn: None 09/18 22:14:55 - mmengine - INFO - ncnn: None 09/18 22:14:55 - mmengine - INFO - snpe: None 09/18 22:14:55 - mmengine - INFO - openvino: None 09/18 22:14:55 - mmengine - INFO - torchscript: 1.8.0 09/18 22:14:55 - mmengine - INFO - torchscript custom ops: NotAvailable 09/18 22:14:55 - mmengine - INFO - rknn-toolkit: None 09/18 22:14:55 - mmengine - INFO - rknn-toolkit2: None 09/18 22:14:55 - mmengine - INFO - ascend: None 09/18 22:14:55 - mmengine - INFO - coreml: None 09/18 22:14:55 - mmengine - INFO - tvm: None 09/18 22:14:55 - mmengine - INFO - vacc: None 09/18 22:14:55 - mmengine - INFO -

09/18 22:14:55 - mmengine - INFO - Codebase information 09/18 22:14:55 - mmengine - INFO - mmdet: 3.0.0 09/18 22:14:55 - mmengine - INFO - mmseg: None 09/18 22:14:55 - mmengine - INFO - mmpretrain: None 09/18 22:14:55 - mmengine - INFO - mmocr: None 09/18 22:14:55 - mmengine - INFO - mmagic: None 09/18 22:14:55 - mmengine - INFO - mmdet3d: None 09/18 22:14:55 - mmengine - INFO - mmpose: None 09/18 22:14:55 - mmengine - INFO - mmrotate: None 09/18 22:14:55 - mmengine - INFO - mmaction: None 09/18 22:14:55 - mmengine - INFO - mmrazor: None 09/18 22:14:55 - mmengine - INFO - mmyolo: None

azuryl avatar Sep 19 '23 02:09 azuryl