-
Notifications
You must be signed in to change notification settings - Fork 5.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
windows paddlepaddle 3.0.0b1 cpu版本相比2.6.1版本存在明显的效率下降 #66697
Comments
请问同学使用的是动态图模式还是开启了动转静呢?另外GPU下是否存在此问题呢? |
不太会用这么复杂的操作,就直接用paddleocr直接传cv2格式的图片进去ocr,别的参数都没调。 |
在i7-12700+3060ti的这台机器上成功运行了2.6.1和3.0.0b1的gpu版本,也没出现import错误。 |
好的,因为之前重点关注的是GPU下的性能效率,windows CPU的效率问题目前的优先级不太高,我们后续会排期处理一下。感谢同学的反馈~ |
linux在docker镜像中同样是paddleocr 2.8.1,--use_gpu false时3.0.0b1耗时明显比2.6.1长 |
bug描述 Describe the Bug
使用场景为paddleocr,对固定数量的图片进行ocr识别
paddleocr为最新2.8.1版本
paddlepaddle为2.6.1和3.0.0b1版本,2.6.1版本使用pypi源直装,3.0.0b1使用官网地址安装
python -m pip install paddlepaddle==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
测试代码:
测试用例:
ocr_test.zip
测试时间:
2.6.1 Total time taken: 26.212960720062256 seconds
3.0.0b1 Total time taken: 65.2573401927948 seconds
测试平台: windows11,i7-12700
另外我在其他的ubuntu机器和macos机器上测试,差异好像没有windows这么大,大概慢10%~20%
其他补充信息 Additional Supplementary Information
No response
The text was updated successfully, but these errors were encountered: