Replies: 3 comments
-
麻烦根据不同版本的模型做一下profile,根据profile的结果看看具体慢的OP是哪些,找出v4模型相对v3模型的性能diff在哪里。 如果有具体结果后还请在issue下回复,我们好进一步跟进~ |
Beta Was this translation helpful? Give feedback.
-
This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions. |
Beta Was this translation helpful? Give feedback.
-
This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions. |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
测试图片为洗发水广告图片。
环境:windows,2核4G内存,指令集只有AVX2,
1.使用飞桨2.5.1版本预测库,使用PPOCRV3模型,识别1秒,使用PPOCRV4模型,75秒
2.使用飞桨2.4.1版本预测库,使用PPOCRV3模型,识别1秒,使用PPOCRV4模型,报错
3.使用openvino底层,使用PPOCRV3模型,识别1秒,使用PPOCRV4模型,1秒
4.使用飞桨2.5.1版本预测库,在AVX512指令集下,使用PPOCRV3、PPOCRV4模型,识别均不到1秒。
5.使用openvino底层,在AVX512指令集下,使用PPOCRV3、PPOCRV4模型,识别均不到0.5秒。
疑问:是不是V4模型有什么算子不支持AVX2指令集,至少要求AVX512了?
这速度根本无法部署应用。
希望能解决这个问题。
Beta Was this translation helpful? Give feedback.
All reactions