Win10下编译OnnxRuntime+OneDNN时
出现 “const_iterator”: 未声明的标识符等错误
如下:
E:\ProgramData\Anaconda3\Library\include\gmock\gmock-matchers.h(2583,33): error C2065: “const_iterator”: 未声明的标识符 [G:\FromGithub\onnxruntime\build\Windows\Release\onnxruntime_test_utils.vcxproj]
(编译源文件“…/…/…/onnxruntime/test/util/test_utils.cc”)

卸载Anaconda或直接使用Python -m venv <虚拟环境>后,再运行Build.bat

GitHub 加速计划 / on / onnxruntime
13.76 K
2.79 K
下载
microsoft/onnxruntime: 是一个用于运行各种机器学习模型的开源库。适合对机器学习和深度学习有兴趣的人,特别是在开发和部署机器学习模型时需要处理各种不同框架和算子的人。特点是支持多种机器学习框架和算子,包括 TensorFlow、PyTorch、Caffe 等,具有高性能和广泛的兼容性。
最近提交(Master分支:23 天前 )
6d7235ba ### Description Exposes `SetDeterministicCompute` in Java, added to the C API by #18944. ### Motivation and Context Parity between C and Java APIs. 17 小时前
02e00dc0 ### Description Adds support for constructing an `OrtSession` from a `java.nio.ByteBuffer`. These buffers can be memory mapped from files which means there doesn't need to be copies of the model protobuf held in Java, reducing peak memory usage during session construction. ### Motivation and Context Reduces memory usage on model construction by not requiring as many copies on the Java side. Should help with #19599. 20 小时前
Logo

旨在为数千万中国开发者提供一个无缝且高效的云端环境,以支持学习、使用和贡献开源项目。

更多推荐