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
利用mmdet框架训练 和 pth文件本地预测都试过了，都没问题。但是导出 pth 为 onnx 这一步报错
%onnx::Reshape_1217 : Long(2, strides=[1], device=cpu) = onnx::Concataxis=0, scope: mmdet.models.detectors.rtmdet.RTMDet:: # d:\situzhiquan\python project\mmlab\mmpose\mmdeploy-main\mmdeploy\mmcv\ops\nms.py:258:0
%labels : Long(*, *, strides=[201, 1], requires_grad=0, device=cpu) = onnx::Reshape(%onnx::Reshape_1216, %onnx::Reshape_1217), scope: mmdet.models.detectors.rtmdet.RTMDet:: # d:\situzhiquan\python project\mmlab\mmpose\mmdeploy-main\mmdeploy\mmcv\ops\nms.py:258:0
return (%dets, %labels)
04/30 15:12:02 - mmengine - ERROR - d:\situzhiquan\python project\mmlab\mmpose\mmdeploy-main\mmdeploy\apis\core\pipeline_manager.py - pop_mp_output - 80 - mmdeploy.apis.pytorch2onnx.torch2onnx with Call id: 0 failed. exit.
Process finished with exit code 1
Reproduction
在 mmdet 可以成功训练并且本地预测的环境下，执行以下步骤
一、下载 mmdeploy 代码到本地
二、pip install -e .
二、pip install onnxruntime
三、python mmdeploy-main/tools/deploy.py
"mmdeploy-main/configs/mmdet/detection/detection_onnxruntime_dynamic.py"
"data/rtmdet_tiny_triangle.py"
"checkpoint/rtmdet_tiny-18272d07.pth"
"data/test/st.jpg"
--work-dir "checkpoint/onnx/rtmdet"
--dump-info
Environment
(MMlab) D:\situzhiquan\Python Project\MMLAB\MMPose>pip list
Package Version Editable project location
---------------------- ------------ -----------------------------------------------------------
addict 2.4.0
aenum 3.1.16
albucore 0.0.23
albumentations 2.0.5
aliyun-python-sdk-core 2.16.0
aliyun-python-sdk-kms 2.16.5
annotated-types 0.7.0
certifi 2025.1.31
cffi 1.17.1
charset-normalizer 3.4.1
chumpy 0.70
click 8.1.8
colorama 0.4.6
coloredlogs 15.0.1
contourpy 1.3.0
crcmod 1.7
cryptography 44.0.2
cycler 0.12.1
Cython 3.0.12
dill 0.4.0
eval_type_backport 0.2.2
filelock 3.14.0
flatbuffers 25.2.10
fonttools 4.57.0
fsspec 2025.3.2
grpcio 1.71.0
humanfriendly 10.0
idna 3.10
importlib_metadata 8.6.1
importlib_resources 6.5.2
Jinja2 3.1.6
jmespath 0.10.0
json-tricks 3.17.3
kiwisolver 1.4.7
Markdown 3.8
markdown-it-py 3.0.0
MarkupSafe 3.0.2
matplotlib 3.9.4
mdurl 0.1.2
mmcv 2.1.0
mmdeploy 1.3.1 d:\situzhiquan\python project\mmlab\mmpose\mmdeploy-main
mmdet 3.3.0 d:\situzhiquan\python project\mmlab\mmpose\mmdetection-main
mmengine 0.10.7
mmpose 1.3.2 d:\situzhiquan\python project\mmlab\mmpose\mmpose-main
model-index 0.1.11
mpmath 1.3.0
multiprocess 0.70.18
munkres 1.1.4
networkx 3.2.1
numpy 2.0.2
onnx 1.17.0
onnxruntime 1.8.1
opencv-python 4.11.0.86
opencv-python-headless 4.11.0.86
opendatalab 0.0.10
openmim 0.3.9
openxlab 0.1.2
ordered-set 4.1.0
oss2 2.17.0
packaging 24.2
pandas 2.2.3
pillow 11.0.0
pip 25.0
platformdirs 4.3.7
prettytable 3.16.0
protobuf 3.20.2
pycocotools 2.0.8
pycparser 2.22
pycryptodome 3.22.0
pydantic 2.11.3
pydantic_core 2.33.1
Pygments 2.19.1
pyparsing 3.2.3
pyreadline3 3.5.4
python-dateutil 2.9.0.post0
pytz 2023.4
pywin32 310
PyYAML 6.0.2
regex 2024.11.6
requests 2.28.2
rich 13.4.2
scipy 1.13.1
seaborn 0.13.2
setuptools 60.2.0
shapely 2.0.7
simsimd 6.2.1
six 1.17.0
stringzilla 3.12.5
sympy 1.13.1
tabulate 0.9.0
termcolor 3.0.1
terminaltables 3.1.10
tomli 2.2.1
torch 2.6.0+cu124
torchaudio 2.6.0+cu124
torchvision 0.21.0+cu124
tqdm 4.65.2
typing_extensions 4.13.2
typing-inspection 0.4.0
tzdata 2025.2
urllib3 1.26.20
wcwidth 0.2.13
wheel 0.45.1
xtcocotools 1.14.3
yapf 0.43.0
zipp 3.21.0Error traceback
。。。。。。。。上面省略一大堆%onnx开头的信息
%onnx::Reshape_1217 : Long(2, strides=[1], device=cpu) = onnx::Concat[axis=0](%onnx::Concat_1213), scope: mmdet.models.detectors.rtmdet.RTMDet:: # d:\situzhiquan\python project\mmlab\mmpose\mmdeploy-main\mmdeploy\mmcv\ops\nms.py:258:0
%labels : Long(*, *, strides=[201, 1], requires_grad=0, device=cpu) = onnx::Reshape(%onnx::Reshape_1216, %onnx::Reshape_1217), scope: mmdet.models.detectors.rtmdet.RTMDet:: # d:\situzhiquan\python project\mmlab\mmpose\mmdeploy-main\mmdeploy\mmcv\ops\nms.py:258:0
return (%dets, %labels)
04/30 15:12:02 - mmengine - ERROR - d:\situzhiquan\python project\mmlab\mmpose\mmdeploy-main\mmdeploy\apis\core\pipeline_manager.py - pop_mp_output - 80 - `mmdeploy.apis.pytorch2onnx.torch2onnx` with Call id: 0 failed. exit.
Process finished with exit code 1