Update README.md

README.md

@@ -1,6 +1,6 @@
-\n# LayoutLM fine-tuned on FUNSD for Document token classification
+# LayoutLM fine-tuned on FUNSD for Document token classification
 
-## Usage
+## Usage (WIP)
 
 ```python
 import torch
@@ -39,7 +39,7 @@ ocr_df = ocr_df.dropna() \\n               .assign(left_scaled = ocr_df.left*w_s
 
 float_cols = ocr_df.select_dtypes('float').columns
 ocr_df[float_cols] = ocr_df[float_cols].round(0).astype(int)
-ocr_df = ocr_df.replace(r'^\s*$', np.nan, regex=True)
+ocr_df = ocr_df.replace(r'^\s*{{%htmlContent%}}#39;, np.nan, regex=True)
 ocr_df = ocr_df.dropna().reset_index(drop=True)
 ocr_df[:20]