[Feature] 可不可以将依赖的onnxruntime升级一下？

[leashi]

Motivation

mmdeploy依赖的onnxruntime的版本太旧了点。

Related resources

No response

Additional context

No response

[Riki123666]

你是使用预编译的包吗，只支持onnx的1.8.1？

[Magic-Pony]

我尝试了1.12.0可以

[Riki123666]

我尝试了1.12.0可以

我之前试了1.18.1的也可以

[morsa96]

The only maximum version that compiles is the 1.13.1

[amxl56]

How do you solve it, please? . I haven't changed anything, onnxruntime==1.15.1,torch==2.1.0?

Traceback (most recent call last): File "d:\Environment\Miniconda\envs\mmdeploy\lib\site-packages\mmdeploy\utils\utils.py", line 41, in target_wrapper result = target(*args, **kwargs) File "d:\Environment\Miniconda\envs\mmdeploy\lib\site-packages\mmdeploy\apis\visualize.py", line 65, in visualize_model model = task_processor.build_backend_model( File "d:\Environment\Miniconda\envs\mmdeploy\lib\site-packages\mmdeploy\codebase\mmdet\deploy\object_detection.py", line 159, in build_backend_model ... File "d:\Environment\Miniconda\envs\mmdeploy\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 424, in _create_inference_session sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model) onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Load model from mmdeploy_model/faster-rcnn\end2end.onnx failed:Type Error: Type parameter (T) of Optype (Where) bound to different types (tensor(int64) and tensor(float) in node (/Where_11). 01/12 16:56:31 - mmengine - ERROR - mmdeploy/tools/deploy.py - create_process - 82 - visualize onnxruntime model failed.