docs: Update the pdf file path in the operation demonstration (Paddle…

…Paddle#13575)
GreatV · Aug 2, 2024 · d69bf81 · d69bf81
1 parent 9c19e6d
commit d69bf81
Show file tree

Hide file tree

Showing 8 changed files with 26 additions and 26 deletions.
diff --git a/docs/ppstructure/model_train/recovery_to_doc.en.md b/docs/ppstructure/model_train/recovery_to_doc.en.md
@@ -86,14 +86,14 @@ pip3 install pdf2docx-0.0.0-py3-none-any.whl
 ```bash linenums="1"
 # install paddleocr
 pip3 install "paddleocr>=2.6"
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
 ```
 
 Command line:
 
 ```bash linenums="1"
 python3 predict_system.py \
-    --image_dir=ppstructure/recovery/UnrealText.pdf \
+    --image_dir=ppstructure/docs/recovery/UnrealText.pdf \
     --recovery=True \
     --use_pdf2docx_api=True \
     --output=../output/

diff --git a/docs/ppstructure/model_train/recovery_to_doc.md b/docs/ppstructure/model_train/recovery_to_doc.md
@@ -84,14 +84,14 @@ pip3 install pdf2docx-0.0.0-py3-none-any.whl
 ```bash linenums="1"
 # 安装 paddleocr，推荐使用2.6版本
 pip3 install "paddleocr>=2.6"
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
 ```
 
 通过命令行的方式：
 
 ```bash linenums="1"
 python3 predict_system.py \
-    --image_dir=ppstructure/recovery/UnrealText.pdf \
+    --image_dir=ppstructure/docs/recovery/UnrealText.pdf \
     --recovery=True \
     --use_pdf2docx_api=True \
     --output=../output/
@@ -117,7 +117,7 @@ paddleocr --image_dir=ppstructure/docs/table/1.png --type=structure --recovery=t
 # 英文测试图
 paddleocr --image_dir=ppstructure/docs/table/1.png --type=structure --recovery=true --lang='en'
 # pdf测试文件
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --lang='en'
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --lang='en'
 ```
 
 ### 4.1 下载模型

diff --git a/docs/ppstructure/quick_start.en.md b/docs/ppstructure/quick_start.en.md
@@ -76,7 +76,7 @@ Two layout recovery methods are provided, For detailed usage tutorials, please r
 Recovery by using PDF parse (only support pdf as input):
 
 ```bash linenums="1"
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
 ```
 
 Recovery by using OCR：
@@ -171,7 +171,7 @@ from paddleocr import PPStructure,save_structure_res
 ocr_engine = PPStructure(table=False, ocr=True, show_log=True)
 
 save_folder = './output'
-img_path = 'ppstructure/recovery/UnrealText.pdf'
+img_path = 'ppstructure/docs/recovery/UnrealText.pdf'
 result = ocr_engine(img_path)
 for index, res in enumerate(result):
     save_structure_res(res, save_folder, os.path.basename(img_path).split('.')[0], index)
@@ -193,7 +193,7 @@ from PIL import Image
 ocr_engine = PPStructure(table=False, ocr=True, show_log=True)
 
 save_folder = './output'
-img_path = 'ppstructure/recovery/UnrealText.pdf'
+img_path = 'ppstructure/docs/recovery/UnrealText.pdf'
 
 fitz = try_import("fitz")
 imgs = []

diff --git a/docs/ppstructure/quick_start.md b/docs/ppstructure/quick_start.md
@@ -76,7 +76,7 @@ paddleocr --image_dir=ppstructure/docs/table/table.jpg --type=structure --layout
 通过PDF解析(只支持pdf格式的输入)：
 
 ```bash linenums="1"
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
 ```
 
 通过OCR技术：
@@ -89,7 +89,7 @@ paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --rec
 通过PDF解析(只支持pdf格式的输入)：
 
 ```bash linenums="1"
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
 ```
 
 通过OCR技术：
@@ -100,7 +100,7 @@ paddleocr --image_dir=ppstructure/docs/table/1.png --type=structure --recovery=t
 # 英文测试图
 paddleocr --image_dir=ppstructure/docs/table/1.png --type=structure --recovery=true --lang='en'
 # pdf测试文件
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --lang='en'
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --lang='en'
 ```
 
 ### 2.2 Python脚本使用
@@ -189,7 +189,7 @@ from paddleocr import PPStructure,save_structure_res
 ocr_engine = PPStructure(table=False, ocr=True, show_log=True)
 
 save_folder = './output'
-img_path = 'ppstructure/recovery/UnrealText.pdf'
+img_path = 'ppstructure/docs/recovery/UnrealText.pdf'
 result = ocr_engine(img_path)
 for index, res in enumerate(result):
     save_structure_res(res, save_folder, os.path.basename(img_path).split('.')[0], index)
@@ -211,7 +211,7 @@ from PIL import Image
 ocr_engine = PPStructure(table=False, ocr=True, show_log=True)
 
 save_folder = './output'
-img_path = 'ppstructure/recovery/UnrealText.pdf'
+img_path = 'ppstructure/docs/recovery/UnrealText.pdf'
 
 fitz = try_import("fitz")
 imgs = []

diff --git a/ppstructure/docs/quickstart.md b/ppstructure/docs/quickstart.md
@@ -99,7 +99,7 @@ paddleocr --image_dir=ppstructure/docs/table/table.jpg --type=structure --layout
 通过PDF解析(只支持pdf格式的输入)：
 
 ```bash
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
 ```
 
 通过OCR技术：
@@ -112,7 +112,7 @@ paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --rec
 通过PDF解析(只支持pdf格式的输入)：
 
 ```bash
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
 ```
 
 通过OCR技术：
@@ -123,7 +123,7 @@ paddleocr --image_dir=ppstructure/docs/table/1.png --type=structure --recovery=t
 # 英文测试图
 paddleocr --image_dir=ppstructure/docs/table/1.png --type=structure --recovery=true --lang='en'
 # pdf测试文件
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --lang='en'
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --lang='en'
 ```
 
 <a name="22"></a>
@@ -217,7 +217,7 @@ from paddleocr import PPStructure,save_structure_res
 ocr_engine = PPStructure(table=False, ocr=True, show_log=True)
 
 save_folder = './output'
-img_path = 'ppstructure/recovery/UnrealText.pdf'
+img_path = 'ppstructure/docs/recovery/UnrealText.pdf'
 result = ocr_engine(img_path)
 for index, res in enumerate(result):
     save_structure_res(res, save_folder, os.path.basename(img_path).split('.')[0], index)
@@ -239,7 +239,7 @@ from PIL import Image
 ocr_engine = PPStructure(table=False, ocr=True, show_log=True)
 
 save_folder = './output'
-img_path = 'ppstructure/recovery/UnrealText.pdf'
+img_path = 'ppstructure/docs/recovery/UnrealText.pdf'
 
 fitz = try_import("fitz")
 imgs = []

diff --git a/ppstructure/docs/quickstart_en.md b/ppstructure/docs/quickstart_en.md
@@ -101,7 +101,7 @@ Two layout recovery methods are provided, For detailed usage tutorials, please r
 Recovery by using PDF parse (only support pdf as input):
 
 ```bash
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
 ```
 
 Recovery by using OCR：
@@ -200,7 +200,7 @@ from paddleocr import PPStructure,save_structure_res
 ocr_engine = PPStructure(table=False, ocr=True, show_log=True)
 
 save_folder = './output'
-img_path = 'ppstructure/recovery/UnrealText.pdf'
+img_path = 'ppstructure/docs/recovery/UnrealText.pdf'
 result = ocr_engine(img_path)
 for index, res in enumerate(result):
     save_structure_res(res, save_folder, os.path.basename(img_path).split('.')[0], index)
@@ -222,7 +222,7 @@ from PIL import Image
 ocr_engine = PPStructure(table=False, ocr=True, show_log=True)
 
 save_folder = './output'
-img_path = 'ppstructure/recovery/UnrealText.pdf'
+img_path = 'ppstructure/docs/recovery/UnrealText.pdf'
 
 fitz = try_import("fitz")
 imgs = []

diff --git a/ppstructure/recovery/README.md b/ppstructure/recovery/README.md
@@ -110,14 +110,14 @@ pip3 install pdf2docx-0.0.0-py3-none-any.whl
 ```bash
 # install paddleocr
 pip3 install "paddleocr>=2.6"
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
 ```
 
 Command line:
 
 ```bash
 python3 predict_system.py \
-    --image_dir=ppstructure/recovery/UnrealText.pdf \
+    --image_dir=ppstructure/docs/recovery/UnrealText.pdf \
     --recovery=True \
     --use_pdf2docx_api=True \
     --output=../output/

diff --git a/ppstructure/recovery/README_ch.md b/ppstructure/recovery/README_ch.md
@@ -106,14 +106,14 @@ pip3 install pdf2docx-0.0.0-py3-none-any.whl
 ```bash
 # 安装 paddleocr，推荐使用2.6版本
 pip3 install "paddleocr>=2.6"
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true
 ```
 
 通过命令行的方式：
 
 ```bash
 python3 predict_system.py \
-    --image_dir=ppstructure/recovery/UnrealText.pdf \
+    --image_dir=ppstructure/docs/recovery/UnrealText.pdf \
     --recovery=True \
     --use_pdf2docx_api=True \
     --output=../output/
@@ -142,7 +142,7 @@ paddleocr --image_dir=ppstructure/docs/table/1.png --type=structure --recovery=t
 # 英文测试图
 paddleocr --image_dir=ppstructure/docs/table/1.png --type=structure --recovery=true --lang='en'
 # pdf测试文件
-paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --lang='en'
+paddleocr --image_dir=ppstructure/docs/recovery/UnrealText.pdf --type=structure --recovery=true --lang='en'
 ```
 
 <a name="4.1"></a>