python -m onnxsim 报错：RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION ，UpsampleMode) const scale >= 1 was false. Scale value should be greater than or equal to 1.

本文转载自查看原文 2021-02-18 16:55 461

RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: /Users/runner/work/1/s/onnxruntime/core/providers/cpu/tensor/upsample.h:271 void onnxruntime::UpsampleBase::ScalesValidation(const std::vector<float> &, const onnxruntime::UpsampleMode) const scale >= 1 was false. Scale value should be greater than or equal to 1.


原因是在

torch.onnx.export 的时候没有配置opset_version参数，默认是9，如果pytorch >=1.3.0,可以配置成11，否则配置成10
详细见：
https://github.com/microsoft/onnxruntime/issues/5548
#=======
@hariharans29 Thank you for your reply, I re-generated the onnx file. The above mentioned problem happens with opset=9, but when setting opset=10, everything goes on well as expected.

免责声明！

本站转载的文章为个人学习借鉴使用，本站对版权不负任何法律责任。如果侵犯了您的隐私权益，请联系本站邮箱yoyou2525@163.com删除。

猜您在找 Python Tkinter Scale滑块 System.FormatException: Index (zero based) must be greater than or equal to zero and less than the size of the argument list scale()函数 float scale = [[UIScreen mainScreen] scale] Invalid prop: type check failed for prop "value". Expected String, Number, got Boolean with value false. Tkinter之Scale Python GUI编程(Tkinter)14、Scale控件 Python：sklearn中StandardScaler和scale的区别 python报错：Exception Value:can only concatenate str (not "bytes") to str 页面缩放scale