========== mmdeploy tools/check_env.py ==========
03/14 11:33:44 - mmengine - INFO -
03/14 11:33:44 - mmengine - INFO - **********Environmental information**********
03/14 11:33:45 - mmengine - INFO - sys.platform: linux
03/14 11:33:45 - mmengine - INFO - Python: 3.8.15 (default, Nov 24 2022, 15:19:38) [GCC 11.2.0]
03/14 11:33:45 - mmengine - INFO - CUDA available: True
03/14 11:33:45 - mmengine - INFO - numpy_random_seed: 2147483648
03/14 11:33:45 - mmengine - INFO - GPU 0: NVIDIA GeForce GTX 1660 Ti
03/14 11:33:45 - mmengine - INFO - CUDA_HOME: /usr/local/cuda
03/14 11:33:45 - mmengine - INFO - NVCC: Cuda compilation tools, release 11.4, V11.4.48
03/14 11:33:45 - mmengine - INFO - GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
03/14 11:33:45 - mmengine - INFO - PyTorch: 1.10.1
03/14 11:33:45 - 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 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: AVX512
- 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 8.2
- Magma 2.5.2
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, 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,
03/14 11:33:45 - mmengine - INFO - TorchVision: 0.11.2
03/14 11:33:45 - mmengine - INFO - OpenCV: 4.7.0
03/14 11:33:45 - mmengine - INFO - MMEngine: 0.5.0
03/14 11:33:45 - mmengine - INFO - MMCV: 2.0.0rc3
03/14 11:33:45 - mmengine - INFO - MMCV Compiler: GCC 7.5
03/14 11:33:45 - mmengine - INFO - MMCV CUDA Compiler: 11.4
03/14 11:33:45 - mmengine - INFO - MMDeploy: 1.0.0rc3+413cc76
03/14 11:33:45 - mmengine - INFO -
03/14 11:33:45 - mmengine - INFO - **********Backend information**********
03/14 11:33:45 - mmengine - INFO - tensorrt: 8.4.1.5
03/14 11:33:45 - mmengine - INFO - tensorrt custom ops: Available
03/14 11:33:45 - mmengine - INFO - ONNXRuntime: 1.8.1
03/14 11:33:45 - mmengine - INFO - ONNXRuntime-gpu: None
03/14 11:33:45 - mmengine - INFO - ONNXRuntime custom ops: Available
03/14 11:33:45 - mmengine - INFO - pplnn: None
03/14 11:33:45 - mmengine - INFO - ncnn: 1.0.20230202
03/14 11:33:45 - mmengine - INFO - ncnn custom ops: Available
03/14 11:33:45 - mmengine - INFO - snpe: None
03/14 11:33:45 - mmengine - INFO - openvino: 2022.3.0
03/14 11:33:45 - mmengine - INFO - torchscript: 1.10.1
03/14 11:33:45 - mmengine - INFO - torchscript custom ops: NotAvailable
03/14 11:33:45 - mmengine - INFO - rknn-toolkit: None
03/14 11:33:45 - mmengine - INFO - rknn-toolkit2: None
03/14 11:33:45 - mmengine - INFO - ascend: None
03/14 11:33:45 - mmengine - INFO - coreml: None
03/14 11:33:45 - mmengine - INFO - tvm: None
03/14 11:33:45 - mmengine - INFO -
03/14 11:33:45 - mmengine - INFO - **********Codebase information**********
03/14 11:33:45 - mmengine - INFO - mmdet: 3.0.0rc4
03/14 11:33:45 - mmengine - INFO - mmseg: 1.0.0rc3
03/14 11:33:45 - mmengine - INFO - mmcls: 1.0.0rc5
03/14 11:33:45 - mmengine - INFO - mmocr: 1.0.0rc4
03/14 11:33:45 - mmengine - INFO - mmedit: 1.0.0rc4
03/14 11:33:45 - mmengine - INFO - mmdet3d: 1.1.0rc2
03/14 11:33:45 - mmengine - INFO - mmpose: 1.0.0rc0
03/14 11:33:45 - mmengine - INFO - mmrotate: 1.0.0rc0
03/14 11:33:45 - mmengine - INFO - mmaction: 1.0.0rc1
========== param ==========
{"sdk": true, "type": "convert_model", "pth_url": "https://download.openmmlab.com/mmclassification/v0/mobilenet_v2/mobilenet_v2_batch256_imagenet_20200708-3b2dc3af.pth", "runtime": "ort1.8.1", "codebase": "mmcls", "test_data": "https://raw.githubusercontent.com/open-mmlab/mmdeploy/v0.10.0/tests/data/tiger.jpeg", "input_shape": "", "codebase_url": "https://github.com/open-mmlab/mmclassification", "mmdeploy_url": "https://github.com/open-mmlab/mmdeploy/", "quantization": false, "dynamic_input": true, "codebase_branch": "v1.0.0rc5", "mmdeploy_branch": "v1.0.0rc1", "train_config_path": "https://openmmlab-deploee.oss-cn-shanghai.aliyuncs.com/tmp/trainconfig/Ji0e2O.py"}
========== deploy config ==========
onnx_config = dict(
type='onnx',
export_params=True,
keep_initializers_as_inputs=False,
opset_version=11,
save_file='end2end.onnx',
input_names=['input'],
output_names=['output'],
input_shape=None,
optimize=True,
dynamic_axes=dict(
input=dict({
0: 'batch',
2: 'height',
3: 'width'
}),
output=dict({0: 'batch'})))
codebase_config = dict(type='mmcls', task='Classification')
backend_config = dict(type='onnxruntime')
========== mmdeploy tools/deploy.py ==========
python3 tools/deploy.py /tmp/workdir/Jp6P_classification_onnxruntime_dynamic.py /tmp/workdir/Ji0e2O.py /tmp/datadir/mobilenet_v2_batch256_imagenet_20200708-3b2dc3af.pth /tmp/datadir/tiger.jpeg --work-dir /tmp/workdir --device cpu --dump-info
========== stdout ==========
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" in the "mmcls_tasks" registry tree. As a workaround, the current "mmcls_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" in the "mmcls_tasks" registry tree. As a workaround, the current "mmcls_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" in the "mmcls_tasks" registry tree. As a workaround, the current "mmcls_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" in the "mmcls_tasks" registry tree. As a workaround, the current "mmcls_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" in the "mmcls_tasks" registry tree. As a workaround, the current "mmcls_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:48 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:49 - mmengine - INFO - Start pipeline mmdeploy.apis.pytorch2onnx.torch2onnx in subprocess
03/14 11:33:49 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:49 - mmengine - WARNING - Failed to search registry with scope "mmcls" in the "mmcls_tasks" registry tree. As a workaround, the current "mmcls_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:49 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:49 - mmengine - WARNING - The "model" registry in mmcls did not set import location. Fallback to call `mmcls.utils.register_all_modules` instead.
Loads checkpoint by local backend from path: /tmp/datadir/mobilenet_v2_batch256_imagenet_20200708-3b2dc3af.pth
03/14 11:33:49 - mmengine - WARNING - The "transform" registry in mmcls did not set import location. Fallback to call `mmcls.utils.register_all_modules` instead.
03/14 11:33:49 - mmengine - WARNING - DeprecationWarning: get_onnx_config will be deprecated in the future.
03/14 11:33:49 - mmengine - INFO - Export PyTorch model to ONNX: /tmp/workdir/end2end.onnx.
03/14 11:33:49 - mmengine - WARNING - Can not find torch._C._jit_pass_onnx_autograd_function_process, function rewrite will not be applied
03/14 11:33:50 - mmengine - INFO - Execute onnx optimize passes.
03/14 11:33:50 - mmengine - INFO - Finish pipeline mmdeploy.apis.pytorch2onnx.torch2onnx
03/14 11:33:50 - mmengine - INFO - Start pipeline mmdeploy.apis.utils.utils.to_backend in main process
03/14 11:33:50 - mmengine - INFO - Finish pipeline mmdeploy.apis.utils.utils.to_backend
03/14 11:33:50 - mmengine - INFO - visualize onnxruntime model start.
03/14 11:33:51 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:51 - mmengine - WARNING - Failed to search registry with scope "mmcls" in the "mmcls_tasks" registry tree. As a workaround, the current "mmcls_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:51 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:51 - mmengine - WARNING - Failed to search registry with scope "mmcls" in the "backend_classifiers" registry tree. As a workaround, the current "backend_classifiers" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:51 - mmengine - WARNING - The "model" registry in mmcls did not set import location. Fallback to call `mmcls.utils.register_all_modules` instead.
03/14 11:33:51 - mmengine - INFO - Successfully loaded onnxruntime custom ops from /root/workspace/mmdeploy/mmdeploy/lib/libmmdeploy_onnxruntime_ops.so
03/14 11:33:52 - mmengine - WARNING - The "transform" registry in mmcls did not set import location. Fallback to call `mmcls.utils.register_all_modules` instead.
03/14 11:33:52 - mmengine - WARNING - The "visualizer" registry in mmcls did not set import location. Fallback to call `mmcls.utils.register_all_modules` instead.
03/14 11:33:52 - mmengine - WARNING - The "vis_backend" registry in mmcls did not set import location. Fallback to call `mmcls.utils.register_all_modules` instead.
03/14 11:33:52 - mmengine - INFO - visualize onnxruntime model success.
03/14 11:33:52 - mmengine - INFO - visualize pytorch model start.
03/14 11:33:53 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:53 - mmengine - WARNING - Failed to search registry with scope "mmcls" in the "mmcls_tasks" registry tree. As a workaround, the current "mmcls_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:53 - mmengine - WARNING - Failed to search registry with scope "mmcls" 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 "mmcls" is a correct scope, or whether the registry is initialized.
03/14 11:33:53 - mmengine - WARNING - The "model" registry in mmcls did not set import location. Fallback to call `mmcls.utils.register_all_modules` instead.
Loads checkpoint by local backend from path: /tmp/datadir/mobilenet_v2_batch256_imagenet_20200708-3b2dc3af.pth
03/14 11:33:53 - mmengine - WARNING - The "transform" registry in mmcls did not set import location. Fallback to call `mmcls.utils.register_all_modules` instead.
03/14 11:33:53 - mmengine - WARNING - The "visualizer" registry in mmcls did not set import location. Fallback to call `mmcls.utils.register_all_modules` instead.
03/14 11:33:53 - mmengine - WARNING - The "vis_backend" registry in mmcls did not set import location. Fallback to call `mmcls.utils.register_all_modules` instead.
03/14 11:33:53 - mmengine - INFO - visualize pytorch model success.
03/14 11:33:53 - mmengine - INFO - All process success.
========== stderr ==========
None