PPStructureV3如何强制使用cpu来处理? #15202
Unanswered
Benboerba9527
asked this question in
Q&A
Replies: 1 comment
-
您好,在 PPStructureV3() 中传入 device="cpu", 应该就可以了。详细可参考 PP-StructureV3 文档 https://paddlepaddle.github.io/PaddleOCR/main/version3.x/pipeline_usage/PP-StructureV3.html (1)实例化产线对象,具体参数说明如下:部分 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
问题背景:
在VMWare workstation pro 17上部署的VM虚机(ubuntu-22.04.5),无法设置VM直通本地的NVIDIA显卡来使用GPU功能,因此需要在代码中强制使用CPU功能来处理表格,但是PPStructureV3中table_engine函数没有use_gpu类似的参数,因此该如何强制使用CPU?
python3代码:
尝试在代码里最前面指定:
import os
os.environ["CUDA_VISIBLE_DEVICES"] = ""
依然无效
Beta Was this translation helpful? Give feedback.
All reactions