Prerequisite

• I have searched the existing and past issues but cannot get the expected help.
• I have read the FAQ documentation but cannot get the expected help.
• The bug has not been fixed in the latest version.

🐞 Describe the bug

There is a type mismatch in the inputs of /Where_1 node in onnx model graph model. The model can not be loaded.

Traceback (most recent call last):
File "/home/unknown/code/chessvideos/tests/test_onnx_raw.py", line 14, in
session = onnxruntime.InferenceSession(
File "/home/unknown/miniconda3/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 347, in init
self._create_inference_session(providers, provider_options, disabled_optimizers)
File "/home/unknown/miniconda3/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 384, 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 /home/unknown/code/chessvideos/models/global/rtmdet_tiny_nms.onnx failed:Type Error: Type parameter (T) of Optype (Where) bound to different types (tensor(int64) and tensor(float) in node (/Where_1).

Environment

torch 2.1.0
cuda 12.1
mmengine>=0.6.0
mmcv 2.1.0
mmdet 3.3.0

Additional information

• code used to export the model to onnx:

!python /content/mmyolo/projects/easydeploy/tools/export_onnx.py
/content/mmyolo/work_dirs/custom/20240413_200608/vis_data/config.py
/content/epoch_10.pth
--work-dir work_dirs/rtmdet
--img-size 640 640
--batch 1
--device cpu
--simplify
--pre-topk 1000
--keep-topk 100
--iou-threshold 0.80
--score-threshold 0.20