Error in loading ONNX model with ONNXRuntime

Question

I'm converting a customized Pytorch model to ONNX. However, when loading it with ONNXRuntime, I've encountered an error as follows:

onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: ...onnxruntime/core/providers/cpu/tensor/transpose.h:46 onnxruntime::TransposeBase::TransposeBase(const onnxruntime::OpKernelInfo &) v >= 0 && static_cast<uint64_t>(v) <= std::numeric_limits<size_t>::max() was false.

I've checked with onnx.checker.check_model() and it's totally fine. I've also tried to replace transpose() into permute() in forward() function but the error has still remained.

Is anyone familiar with this error?

Environments:

Python 3.7
Pytorch 1.9.0
CUDA 10.2 
ONNX 1.10.1
ONNXRuntime 1.8.1 
OS Ubuntu 18.04

@SergiiDymchenko It's here (onnx file). Thank you in advance. — nguyendhn
– nguyendhn, Commented Aug 16, 2021 at 4:44
The perm attribute of node Transpose_52 is [-1, 0, 1] although ONNX Runtime requires that all of them should be positive: github.com/microsoft/onnxruntime/blob/… — dkim
– dkim, Commented Aug 16, 2021 at 5:06
Oh. Thank you a lot. I had thought that we only need to change from transpose() to permute() and don't need to pay attention to those indices. It makes sense now. Thank you @dkim. — nguyendhn
– nguyendhn, Commented Aug 16, 2021 at 5:11
@dkim Can you post in the term of an answer so that I can accept it? — nguyendhn
– nguyendhn, Commented Aug 16, 2021 at 5:12

dkim · Accepted Answer · 2021-08-16 05:18:17Z

3

The perm attribute of node Transpose_52 is [-1, 0, 1] although ONNX Runtime requires that all of them should be positive: onnxruntime/core/providers/cpu/tensor/transpose.h#L46

answered Aug 16, 2021 at 5:18

dkim

3,9801 gold badge37 silver badges39 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Error in loading ONNX model with ONNXRuntime

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related