x86 ubuntu 使用mobilenet_v1转换后的模型报错

[ZHAOSHICHEN94]

程序运行到std::shared_ptr<PaddlePredictor> predictor =CreatePaddlePredictor<MobileConfig>(config);报错

报错信息如下： W0707 17:08:56.148413 11192 dynamic_loader.cc:121] Can not find library: libmklml_intel.so. The process maybe hang. Please try to add the lib path to LD_LIBRARY_PATH. F0707 17:08:56.148521 11192 dynamic_loader.cc:180] Check failed: dso_handle != nullptr *** Check failure stack trace: ***

[paddle-bot[bot]]

您好，我们已经收到了您的问题，会安排技术人员尽快解答您的问题，请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时，您也可以通过查看官网文档、常见问题、历史Issue来寻求解答。祝您生活愉快～

Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the API，FAQ and Github Issue to get the answer.Have a nice day!

[hong19860320]

运行的时候需要保证系统能够找到 libmklml_intel.so ，可以在我们的 PaddleLite-generic-demo 中的 PaddleLite-generic-demo/libs/PaddleLite/linux/amd64/lib/cpu 中找到，当然你甚至可以基于 PaddleLite-generic-demo 一键运行图像分类示例，例如：

$ cd PaddleLite-generic-demo/image_classification_demo/shell/
$ ./run.sh mobilenet_v1_fp32_224 linux amd64

上述命令来源于 https://www.paddlepaddle.org.cn/lite/develop/demo_guides/huawei_ascend_npu.html

[ZHAOSHICHEN94]

我电脑是amd的cpu，libmklml_intel.so是amd也可以用的吗？

[hong19860320]

我电脑是amd的cpu，libmklml_intel.so是amd也可以用的吗？

可以试试看，我们只在intel x86 cpu 验证过