doc/doc_ch/table_recognition.md下推理预测时的infer_table.py只能一张张推理速度太慢了，能否将eval.py时的多张验证的功能迁移过来，以此提升推理速度 #12376
Unanswered
a-strong-python
asked this question in
Q&A
doc/doc_ch/table_recognition.md下推理预测时的infer_table.py只能一张张推理速度太慢了，能否将eval.py时的多张验证的功能迁移过来，以此提升推理速度
#12376
Replies: 1 comment
-
|
5w张测试集推理半个小时还没推理完，显卡只用到了40%的算力 |
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.
-
doc/doc_ch/table_recognition.md下推理预测时的infer_table.py只能一张张推理速度太慢了，能否将eval.py时的多张验证的功能迁移过来，以此提升推理速度。
其实就是训练和验证时导入的config.yml中的batch_size_per_card这个参数能否迁移到infer_table.py中，如果可以，能否提供一些思路
Beta Was this translation helpful? Give feedback.
All reactions