RuntimeError: Assertion false failed: No Adapter From Version $20 for GridSample

[jikechao]

Describe the issue

Converting the model opset version failed. By checking the document about GridSample, I found that opset 20 is a valid version for GridSample.

Traceback (most recent call last):
  File "test.py", line 247, in <module>
    combine_models_random(seed_model, donor_model, position_flag='random')
  File "test.py", line 221, in combine_models_random
    donor_model = onnx.version_converter.convert_version(donor_model, 16)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/miniconda3/lib/python3.12/site-packages/onnx/version_converter.py", line 37, in convert_version
    converted_model_str = C.convert_version(model_str, target_version)
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: /github/workspace/onnx/version_converter/BaseConverter.h:73: adapter_lookup: Assertion `false` failed: No Adapter From Version $20 for GridSample

To reproduce

import onnx
model = onnx.load("...")
new_model = onnx.version_converter.convert_version(model, 16)

Urgency

No response

Platform

Linux

OS Version

Ubuntu 20.04

ONNX Runtime Installation

Built from Source

ONNX Runtime Version or Commit ID

latest-version

ONNX Runtime API

Python

Architecture

X64

Execution Provider

Default CPU

Execution Provider Library Version

No response

[gramalingam]

Hi, do you have an example model to repro this? Thanks!