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
我在导出mmdet3d模型的时候遇到如下的错误，无论我用那个配置文件
export MODEL_CONFIG=mmdetection3d/configs/smoke/smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d.py
export MODEL_PATH=mmdetection3d/checkpoints/smoke_dla34_pytorch_dlaneck_gn-all_8x4_6x_kitti-mono3d_20210929_015553-d46d9bb0.pth
export TEST_DATA=mmdetection3d/demo/data/kitti/000008.png
用
python mmdeploy/tools/deploy.py
mmdeploy/configs/mmdet3d/mono-detection/mono-detection_static.py
$MODEL_CONFIG
$MODEL_PATH
$TEST_DATA
--work-dir deploy_models/mmdet3d/smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d
--device cpu
--dump-info
报错：
home/miniconda3/envs/torch2.5.1/lib/python3.10/site-packages/mmengine/optim/optimizer/zero_optimizer.py:11: DeprecationWarning: TorchScript support for functional optimizers is deprecated and will be removed in a future PyTorch release. Consider using the torch.compile optimizer instead.
from torch.distributed.optim import
/home/miniconda3/envs/torch2.5.1/lib/python3.10/site-packages/mmengine/optim/optimizer/zero_optimizer.py:11: DeprecationWarning: TorchScript support for functional optimizers is deprecated and will be removed in a future PyTorch release. Consider using the torch.compile optimizer instead.
from torch.distributed.optim import
Traceback (most recent call last):
File "/dataset/workspace/openmmlab/mmdeploy/tools/deploy.py", line 335, in
main()
File "/dataset/workspace/openmmlab/mmdeploy/tools/deploy.py", line 129, in main
export2SDK(
File "/dataset/workspace/openmmlab/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 352, in export2SDK
deploy_info = get_deploy(deploy_cfg, model_cfg, work_dir, device)
File "/dataset/liuhongyuan/workspace/openmmlab/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 266, in get_deploy
cls_name = task_map[task]['cls_name']
KeyError: <Task.MONO_DETECTION: 'MonoDetection'>
用
python mmdeploy/tools/deploy.py
mmdeploy/configs/mmdet3d/voxel-detection/voxel-detection_onnxruntime_dynamic.py
$MODEL_CONFIG
$MODEL_PATH
$TEST_DATA
--work-dir deploy_models/mmdet3d/smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d
--device cpu
--dump-info
报错：
/home/miniconda3/envs/torch2.5.1/lib/python3.10/site-packages/mmengine/optim/optimizer/zero_optimizer.py:11: DeprecationWarning: TorchScript support for functional optimizers is deprecated and will be removed in a future PyTorch release. Consider using the torch.compile optimizer instead.
from torch.distributed.optim import
/home/miniconda3/envs/torch2.5.1/lib/python3.10/site-packages/mmengine/optim/optimizer/zero_optimizer.py:11: DeprecationWarning: TorchScript support for functional optimizers is deprecated and will be removed in a future PyTorch release. Consider using the torch.compile optimizer instead.
from torch.distributed.optim import
Traceback (most recent call last):
File "/dataset/workspace/openmmlab/mmdeploy/tools/deploy.py", line 335, in
main()
File "/dataset/workspace/openmmlab/mmdeploy/tools/deploy.py", line 129, in main
export2SDK(
File "/dataset/workspace/openmmlab/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 354, in export2SDK
deploy_info = get_deploy(deploy_cfg, model_cfg, work_dir, device)
File "/dataset/workspace/openmmlab/mmdeploy/mmdeploy/backend/sdk/export_info.py", line 268, in get_deploy
cls_name = task_map[task]['cls_name']
KeyError: <Task.VOXEL_DETECTION: 'VoxelDetection'>
我的环境是：
mmcv 2.1.0
mmdeploy 1.3.1
mmdeploy-runtime 1.2.0
mmdeploy-runtime-gpu 1.2.0
mmdet 3.2.0
mmdet3d 1.4.0
mmengine 0.10.6
mmpretrain 1.2.0
torch 2.5.1+cu124
torchaudio 2.5.1+cu124
torchsummary 1.5.1
torchvision 0.20.1+cu124
Reproduction
python mmdeploy/tools/deploy.py
mmdeploy/configs/mmdet3d/mono-detection/mono-detection_static.py
$MODEL_CONFIG
$MODEL_PATH
$TEST_DATA
--work-dir deploy_models/mmdet3d/smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d
--device cpu
--dump-info
or
python mmdeploy/tools/deploy.py
mmdeploy/configs/mmdet3d/voxel-detection/voxel-detection_onnxruntime_dynamic.py
$MODEL_CONFIG
$MODEL_PATH
$TEST_DATA
--work-dir deploy_models/mmdet3d/smoke_dla34_dlaneck_gn-all_4xb8-6x_kitti-mono3d
--device cpu
--dump-info
Environment
01/18 01:41:32 - mmengine - INFO -
01/18 01:41:32 - mmengine - INFO - **********Environmental information**********
/home/liuhongyuan/miniconda3/envs/torch2.5.1/lib/python3.10/site-packages/mmengine/optim/optimizer/zero_optimizer.py:11: DeprecationWarning: `TorchScript` support for functional optimizers is deprecated and will be removed in a future PyTorch release. Consider using the `torch.compile` optimizer instead.
from torch.distributed.optim import \
01/18 01:41:33 - mmengine - INFO - sys.platform: linux
01/18 01:41:33 - mmengine - INFO - Python: 3.10.15 (main, Oct 3 2024, 07:27:34) [GCC 11.2.0]
01/18 01:41:33 - mmengine - INFO - CUDA available: True
01/18 01:41:33 - mmengine - INFO - MUSA available: False
01/18 01:41:33 - mmengine - INFO - numpy_random_seed: 2147483648
01/18 01:41:33 - mmengine - INFO - GPU 0,1,2,3,4,5,6,7: NVIDIA GeForce RTX 4090
01/18 01:41:33 - mmengine - INFO - CUDA_HOME: /usr/local/cuda-12.4
01/18 01:41:33 - mmengine - INFO - NVCC: Cuda compilation tools, release 12.4, V12.4.99
01/18 01:41:33 - mmengine - INFO - GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
01/18 01:41:33 - mmengine - INFO - PyTorch: 2.5.1+cu124
01/18 01:41:33 - mmengine - INFO - PyTorch compiling details: PyTorch built with:
- GCC 9.3
- C++ Version: 201703
- Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v3.5.3 (Git Hash 66f0cb9eb66affd2da3bf5f8d897376f04aae6af)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX512
- CUDA Runtime 12.4
- NVCC architecture flags: -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;-gencode;arch=compute_90,code=sm_90
- CuDNN 90.1
- Magma 2.6.1
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.4, CUDNN_VERSION=9.1.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -Wno-missing-braces -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, TORCH_VERSION=2.5.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF,
01/18 01:41:33 - mmengine - INFO - TorchVision: 0.20.1+cu124
01/18 01:41:33 - mmengine - INFO - OpenCV: 4.10.0
01/18 01:41:33 - mmengine - INFO - MMEngine: 0.10.6
01/18 01:41:33 - mmengine - INFO - MMCV: 2.1.0
01/18 01:41:33 - mmengine - INFO - MMCV Compiler: GCC 11.4
01/18 01:41:33 - mmengine - INFO - MMCV CUDA Compiler: 12.4
01/18 01:41:33 - mmengine - INFO - MMDeploy: 1.3.1+
01/18 01:41:33 - mmengine - INFO -
01/18 01:41:33 - mmengine - INFO - **********Backend information**********
01/18 01:41:33 - mmengine - INFO - tensorrt: 8.6.1
01/18 01:41:33 - mmengine - INFO - tensorrt custom ops: NotAvailable
01/18 01:41:33 - mmengine - INFO - ONNXRuntime: 1.20.1
01/18 01:41:33 - mmengine - INFO - ONNXRuntime-gpu: 1.20.1
01/18 01:41:33 - mmengine - INFO - ONNXRuntime custom ops: NotAvailable
01/18 01:41:33 - mmengine - INFO - pplnn: None
01/18 01:41:33 - mmengine - INFO - ncnn: None
01/18 01:41:33 - mmengine - INFO - snpe: None
01/18 01:41:33 - mmengine - INFO - openvino: None
01/18 01:41:33 - mmengine - INFO - torchscript: 2.5.1+cu124
01/18 01:41:33 - mmengine - INFO - torchscript custom ops: NotAvailable
01/18 01:41:34 - mmengine - INFO - rknn-toolkit: None
01/18 01:41:34 - mmengine - INFO - rknn-toolkit2: None
01/18 01:41:34 - mmengine - INFO - ascend: None
01/18 01:41:34 - mmengine - INFO - coreml: None
01/18 01:41:34 - mmengine - INFO - tvm: None
01/18 01:41:34 - mmengine - INFO - vacc: None
01/18 01:41:34 - mmengine - INFO -
01/18 01:41:34 - mmengine - INFO - **********Codebase information**********
01/18 01:41:34 - mmengine - INFO - mmdet: 3.2.0
01/18 01:41:34 - mmengine - INFO - mmseg: None
01/18 01:41:34 - mmengine - INFO - mmpretrain: 1.2.0
01/18 01:41:34 - mmengine - INFO - mmocr: None
01/18 01:41:34 - mmengine - INFO - mmagic: None
01/18 01:41:34 - mmengine - INFO - mmdet3d: 1.4.0
01/18 01:41:34 - mmengine - INFO - mmpose: None
01/18 01:41:34 - mmengine - INFO - mmrotate: None
01/18 01:41:34 - mmengine - INFO - mmaction: None
01/18 01:41:34 - mmengine - INFO - mmrazor: None
01/18 01:41:34 - mmengine - INFO - mmyolo: None