Paddle ocr structure 和 ocr model 在 H800 GPU 上输出结果为 空 #12661
Unanswered
itsliupeng
asked this question in
Q&A
Replies: 4 comments
-
我也遇到了相同的问题,使用H800,模型初始化后的预测结果都不同,有时为空。同台机器上,不使用H800只使用CPU可正常输出 |
Beta Was this translation helpful? Give feedback.
0 replies
-
我也遇到了相同的问题,使用H800模型预测结果为空,但是使用CPU预测正常 |
Beta Was this translation helpful? Give feedback.
0 replies
-
我也遇到了在H800上使用GPU预测输出为空的问题,在使用CPU预测时可以正常输出 |
Beta Was this translation helpful? Give feedback.
0 replies
-
这种感觉是PaddlePaddle推理框架的原因,上边遇到的小伙伴,可以验证一下paddlepaddle-gpu是否可以正常使用呢? import paddle
paddle.utils.run_check()
# 看看会不会说successfully |
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.
-
运行命令:paddleocr --image_dir=ppstructure/docs/table/1.png --type=structure --table=false --ocr=true
使用 https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/ppstructure/README_ch.md 这里面的模型来识别 pdf
Paddle ocr structure 和 ocr model 在 H800 GPU 上输出结果为 空, 但在 CPU 和 A800 GPU 上正常,请问下具体原因
Beta Was this translation helpful? Give feedback.
All reactions