如何避免出现复读现象?
            
            #16804
          
          
        Replies: 2 comments
-
| predict(input, *, use_doc_orientation_classify=None, use_doc_unwarping=None, use_layout_detection=None, use_chart_recognition=None, layout_threshold=None, layout_nms=None, layout_unclip_ratio=No 查看了这些参数,是可以显示的使用 repetition_penalty 来修改的,,那么,,我应该设置为多少比较好呢? | 
Beta Was this translation helpful? Give feedback.
                  
                    0 replies
                  
                
            -
| 设置为1.5,好像没有用啊? | 
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.
-
我使用的官方教程 section2.2,parse pdf的方法,导入本地的模型,但是出现了复读现象,

如:
原图:

文字在文本框中且较密集。
但是我看到pipeline中无法设置惩罚项,请问要怎么做才能避免这类问题呢?
Beta Was this translation helpful? Give feedback.
All reactions