Open EthanZhangYi opened 2 years ago
@daquexian Could you please give some help?
When I downgrade the pkg version to
No error is raised.
same problem
onnx==1.12.0
onnx-simplifier==0.4.0
onnxconverter-common @ git+https://github.com/microsoft/onnxconverter-common@0a401de9ee410bf3f65fb3dd3d13d4eab7e91a10
onnxmltools==1.11.1
onnxruntime==1.11.1
onnxsim-no-ort==0.4.0
skl2onnx==1.11.2
tf2onnx==1.11.1
In my case MemoryError: std::bad_alloc
and segmentation faults depend on the opset.
Version 11
faults while 10
not. Opset version 11
also introduced dynamic shape capabilities.
onnx==1.11.0
onnx-simplifier==0.3.10
onnxoptimizer==0.2.7
onnxruntime==1.11.1
onnxsim==0.4.7
onnxsim-no-ort==0.4.0
thanks @ahirner , having the same issue. Setting opset=10, does not crash but opset=11, crashes with bad_alloc
same observation here: bad_alloc with opset >= 11, when using the python API (onnxsim.simpify) strange thing is that when I use the command line tool (onnxsim), the model optimizes just fine
I also observed the the error is nondeterministic. Looking at onnx2f, is seems like they cam e to the same conclusion:https://github.com/PINTO0309/onnx2tf/blob/794bd8699b55ea74c09411fd1d077448e02954aa/onnx2tf/onnx2tf.py#L505-L536
this looks like a serious issue @daquexian.
see small example i provided there #206
Describe the bug A error
Segmentation fault (core dumped)
is raised when usingonnxsim
.Environment
Model A test script is provided.
If we use
skipped_optimizers=['extract_constant_to_initializer']
,segmentation fault
is raised. If we comment this line, everything is OK. However, in my project, this line is needed.