Run official model fasterrcnn failed by onnxruntime

Bug Report

Which model does this pertain to?

FasterRCNN-12.onnx
(https://github.com/onnx/models/blob/main/vision/object_detection_segmentation/faster-rcnn/model/FasterRCNN-12.onnx)

Describe the bug

onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Add node. Name:'451' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/math/element_wise_ops.h:503 void onnxruntime::BroadcastIterator::Init(ptrdiff_t, ptrdiff_t) axis == 1 || axis == largest was false. Attempting to broadcast an axis by a dimension other than 1. 75 by 76

Reproduction instructions

System Information
onnxruntime versiont 1.12.1
numpy version 1.23.4
python version 3.8.8

Provide a code snippet to reproduce your errors.

import numpy
from onnxruntime import InferenceSession, RunOptions

X = numpy.ones([3,600,600], dtype="float32")
sess = InferenceSession("FasterRCNN-12.onnx")
names = [o.name for o in sess._sess.outputs_meta]
ro = RunOptions()
result = sess._sess.run(names, {'image': X}, ro)
...

Notes

Any additional information

Start with the linked FasterRCNN-12.onnx model and run the supplied Python reproduction using InferenceSession and the image input. Investigate the reported Add node broadcast failure, including the 75 by 76 dimension mismatch. Done means the official model runs successfully with the shown input without the ONNX Runtime exception.