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.

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

add opset-15 #1731

Merged
merged 6 commits into from
Oct 6, 2021
Merged

add opset-15 #1731

merged 6 commits into from
Oct 6, 2021

Conversation

guschmue
Copy link
Contributor

Signed-off-by: Guenther Schmuelling guschmue@microsoft.com

Signed-off-by: Guenther Schmuelling <guschmue@microsoft.com>
Signed-off-by: Guenther Schmuelling <guschmue@microsoft.com>
Signed-off-by: Guenther Schmuelling <guschmue@microsoft.com>
@guschmue
Copy link
Contributor Author

guschmue commented Oct 5, 2021

run_pretrained_models.py fails with a crash in onnx/shapeinference for opset-15. opset-14 is fine.

Thread 1 "python" received signal SIGSEGV, Segmentation fault.
0x00007fff7b6d8b20 in std::_Function_handler<void (onnx::InferenceContext&), onnx::GetOpSchemaonnx::Shape_Onnx_ver15()::{lambda(onnx::InferenceContext&)#1}>::_M_invoke(std::_Any_data const&, onnx::InferenceContext&) ()
from /opt/anaconda3/lib/python3.7/site-packages/onnx/onnx_cpp2py_export.cpython-37m-x86_64-linux-gnu.so
(gdb) bt
#0 0x00007fff7b6d8b20 in std::_Function_handler<void (onnx::InferenceContext&), onnx::GetOpSchemaonnx::Shape_Onnx_ver15()::{lambda(onnx::InferenceContext&)#1}>::_M_invoke(std::_Any_data const&, onnx::InferenceContext&) ()
from /opt/anaconda3/lib/python3.7/site-packages/onnx/onnx_cpp2py_export.cpython-37m-x86_64-linux-gnu.so
#1 0x00007fff7b7158f3 in onnx::shape_inference::InferShapesImpl(onnx::GraphProto*, std::unordered_map<std::string, onnx::TypeProto*, std::hashstd::string, std::equal_tostd::string, std::allocator<std::pair<std::string const, onnx::TypeProto*> > > const&, std::unordered_map<std::string, int, std::hashstd::string, std::equal_tostd::string, std::allocator<std::pair<std::string const, int> > > const&, onnx::ShapeInferenceOptions const&, onnx::SymbolTable*, onnx::ISchemaRegistry const*, int) ()
from /opt/anaconda3/lib/python3.7/site-packages/onnx/onnx_cpp2py_export.cpython-37m-x86_64-linux-gnu.so
#2 0x00007fff7b716ab5 in onnx::shape_inference::GraphInferencerImpl::doInferencing(std::vector<onnx::TypeProto const*, std::allocator<onnx::TypeProto const*> > const&, std::vector<onnx::TensorProto const*, std::allocator<onnx::TensorProto const*> > const&) ()
from /opt/anaconda3/lib/python3.7/site-packages/onnx/onnx_cpp2py_export.cpython-37m-x86_64-linux-gnu.so
#3 0x00007fff7b5ed8e5 in onnx::LoopInferenceFunction(onnx::InferenceContext&) ()
from /opt/anaconda3/lib/python3.7/site-packages/onnx/onnx_cpp2py_export.cpython-37m-x86_64-linux-gnu.so
#4 0x00007fff7b7158f3 in onnx::shape_inference::InferShapesImpl(onnx::GraphProto*, std::unordered_map<std::string, onnx::TypeProto*, std::hashstd::string, std::equal_tostd::string, std::allocator<std::pair<std::string const, onnx::TypeProto*> > > const&, std::unordered_map<std::string, int, std::hashstd::string, std::equal_tostd::string, std::allocator<std::pair<std::string const, int> > > const&, onnx::ShapeInferenceOptions const&, onnx::SymbolTable*, onnx::ISchemaRegistry const*, int) ()

Signed-off-by: Guenther Schmuelling <guschmue@microsoft.com>
Signed-off-by: Guenther Schmuelling <guschmue@microsoft.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants