-2 opencv module_error ai_generated partial

cv2.error: OpenCV(4.9.0) ../modules/dnn/src/onnx/onnx_importer.cpp:1122: 错误: (-2:未指定错误) 函数 'importNode': OpenCV 不支持 ONNX 算子 'ScatterND'

cv2.error: OpenCV(4.9.0) ../modules/dnn/src/onnx/onnx_importer.cpp:1122: error: (-2:Unspecified error) in function 'importNode': OpenCV does not support ONNX operator 'ScatterND'

ID: opencv/dnn-readnet-from-onnx-unsupported-op

其他格式: JSON · Markdown 中文 · English
80%修复率
87%置信度
1证据数
2024-01-15首次发现

版本兼容性

版本状态引入弃用备注
4.8.0 active — — —
4.9.0 active — — —
4.10.0 active — — —

根因分析

ONNX 模型使用了 OpenCV DNN 模块未实现的算子（例如 ScatterND, NonMaxSuppression）。

English

The ONNX model uses an operator (e.g., ScatterND, NonMaxSuppression) that is not implemented in OpenCV's DNN module.

generic

官方文档

https://docs.opencv.org/4.x/d6/d0f/group__dnn.html

解决方案

  1. Export the ONNX model from PyTorch/TensorFlow with opset version 10 or lower, avoiding newer operators: torch.onnx.export(model, dummy_input, 'model.onnx', opset_version=10)
  2. Use a different inference backend like ONNX Runtime instead of OpenCV DNN: import onnxruntime; session = onnxruntime.InferenceSession('model.onnx')

无效尝试

常见但无效的做法:

  1. 60% 失败

    OpenCV's DNN backend has limited ONNX operator coverage; many ops remain unimplemented across versions.

  2. 80% 失败

    Conversion tools often map unsupported ops to other unsupported ops or fail entirely.