| 12345678910111213141516171819202122 |
- 库需求：
- openCV
- onnxruntime-gpu
- onnxruntime版本需求为：1.16.0
- 存在问题：onnxruntimeC++安装问题
- onnxruntime安装步骤参考为：
- https://blog.csdn.net/LABLENET/article/details/136615836?ops_request_misc=%257B%2522request%255Fid%2522%253A%25226E86B7C2-BF96-4D15-A4B3-5E636040D088%2522%252C%2522scm%2522%253A%252220140713.130102334..%2522%257D&request_id=6E86B7C2-BF96-4D15-A4B3-5E636040D088&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~all~sobaiduend~default-2-136615836-null-null.142^v100^pc_search_result_base4&utm_term=onnxruntime-gpu%E5%AE%89%E8%A3%85linux&spm=1018.2226.3001.4187
- 此环境与AD10基本类似，但实际编译存在问题：
- -- SHA1 hash of
- does not match expected value
- expected: 'ee201b07085203ea7bd8eb97cbcb31b07cfa3efb'
- actual: '7fdb7133e38f370a71c38e82f03458c2b638bd29'
- -- Hash mismatch, removing...
- CMake Error at eigen-subbuild/eigen-populate-prefix/src/eigen-populate-stamp/download-eigen-populate.cmake:170 (message):
- Each download failed!
- 测试结果：
- 1、windows机上，cpu运行速度与python的cpu运行速度一致
- 2、AD10上：需先解决onnxruntimeC++版本的安装问题
|
