Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

TypeError "forward() missing 2 required positional arguments: 'feats' and 'rois'" in pytorch2onnx #34

Open
esdream opened this issue Apr 23, 2021 · 1 comment
Open

TypeError "forward() missing 2 required positional arguments: 'feats' and 'rois'" in pytorch2onnx #34

esdream opened this issue Apr 23, 2021 · 1 comment

Comments

@esdream
Copy link

esdream commented Apr 23, 2021

When I try to convert pytorch model to onnx by running tools/pytorch2onnx.py, I encountered this error.

Script

python tools/pytorch2onnx.py configs/OpenImages_configs/r50-FPN-1x_classsampling_TSD/r50-FPN-1x_classsampling_TSD.py checkpoints/r50-FPN-1x_classsampling_TSD.pth --out r50-FPN-1x_classsampling_TSD.onnx

Environment

sys.platform: linux
Python: 3.7.5 (default, Oct 25 2019, 15:51:11) [GCC 7.3.0]
CUDA available: True
CUDA_HOME: /usr/local/cuda-10.1
NVCC: Cuda compilation tools, release 10.1, V10.1.105
GPU 0: GeForce RTX 2080 Ti
GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609
PyTorch: 1.2.0
PyTorch compiling details: PyTorch built with:

  • GCC 7.3
  • Intel(R) Math Kernel Library Version 2019.0.4 Product Build 20190411 for Intel(R) 64 architecture applications
  • Intel(R) MKL-DNN v0.18.1
  • OpenMP 201511 (a.k.a. OpenMP 4.5)
  • NNPACK is enabled
  • CUDA Runtime 10.0
  • NVCC architecture flags: -gencode;arch=compute_35,code=sm_35;-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_50,code=compute_50
  • CuDNN 7.6.2
  • Magma 2.5.1
  • Build settings: BLAS=MKL, BUILD_NAMEDTENSOR=OFF, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DUSE_FBGEMM -DUSE_QNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -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-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -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 -Wno-stringop-overflow, DISABLE_NUMA=1, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=True, 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,

TorchVision: 0.4.0
OpenCV: 4.1.1
MMCV: 0.4.3
MMDetection: 1.1.0+fb1fdd7
MMDetection Compiler: GCC 5.4
MMDetection CUDA Compiler: 10.1

Error traceback

/content/anaconda3/envs/face/lib/python3.7/site-packages/mmdet-1.1.0+fb1fdd7-py3.7-linux-x86_64.egg/mmdet/core/bbox/transforms.py:163: 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 bboxes.size(0) > 0:
/content/anaconda3/envs/face/lib/python3.7/site-packages/mmdet-1.1.0+fb1fdd7-py3.7-linux-x86_64.egg/mmdet/models/roi_extractors/single_level.py:99: 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 inds.any():
/content/anaconda3/envs/face/lib/python3.7/site-packages/mmdet-1.1.0+fb1fdd7-py3.7-linux-x86_64.egg/mmdet/ops/roi_align/roi_align.py:149: 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 rois.dim() == 2 and rois.size(1) == 5
Traceback (most recent call last):
  File "tools/pytorch2onnx.py", line 127, in <module>
    main()
  File "tools/pytorch2onnx.py", line 119, in main
    onnx_model = export_onnx_model(model, (input_data,), args.passes)
  File "tools/pytorch2onnx.py", line 44, in export_onnx_model
    operator_export_type=OperatorExportTypes.ONNX_ATEN_FALLBACK,
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/onnx/__init__.py", line 132, in export
    strip_doc_string, dynamic_axes)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/onnx/utils.py", line 64, in export
    example_outputs=example_outputs, strip_doc_string=strip_doc_string, dynamic_axes=dynamic_axes)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/onnx/utils.py", line 329, in _export
    _retain_param_name, do_constant_folding)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/onnx/utils.py", line 213, in _model_to_graph
    graph, torch_out = _trace_and_get_graph_from_model(model, args, training)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/onnx/utils.py", line 171, in _trace_and_get_graph_from_model
    trace, torch_out = torch.jit.get_trace_graph(model, args, _force_outplace=True)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/jit/__init__.py", line 256, in get_trace_graph
    return LegacyTracedModule(f, _force_outplace, return_inputs)(*args, **kwargs)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/jit/__init__.py", line 323, in forward
    out = self.inner(*trace_inputs)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/nn/modules/module.py", line 545, in __call__
    result = self._slow_forward(*input, **kwargs)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/nn/modules/module.py", line 531, in _slow_forward
    result = self.forward(*input, **kwargs)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/mmdet-1.1.0+fb1fdd7-py3.7-linux-x86_64.egg/mmdet/models/detectors/two_stage.py", line 128, in forward_dummy
    cls_score, bbox_pred = self.bbox_head(bbox_feats)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/nn/modules/module.py", line 545, in __call__
    result = self._slow_forward(*input, **kwargs)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/torch/nn/modules/module.py", line 531, in _slow_forward
    result = self.forward(*input, **kwargs)
  File "/content/anaconda3/envs/face/lib/python3.7/site-packages/mmdet-1.1.0+fb1fdd7-py3.7-linux-x86_64.egg/mmdet/core/fp16/decorators.py", line 130, in new_func
    return old_func(*args, **kwargs)
TypeError: forward() missing 2 required positional arguments: 'feats' and 'rois'

Thanks a lot!
@qjh666888
Copy link

请问解决了吗

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@esdream @qjh666888