Duplicate from onursavas/Chinese_Document_Layout_Analysis

Co-authored-by: Onur Savas <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+0.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Chinese Document Layout Analysis
+emoji: 🏢
+colorFrom: pink
+colorTo: purple
+sdk: gradio
+sdk_version: 3.24.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: onursavas/Chinese_Document_Layout_Analysis
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+import os
+import cv2
+import numpy as np
+from paddleocr import PPStructure,save_structure_res
+from paddleocr.ppstructure.recovery.recovery_to_doc import sorted_layout_boxes, convert_info_docx
+
+# Chinese image
+table_engine = PPStructure(recovery=True)
+
+# English image
+# table_engine = PPStructure(recovery=True, lang='en')
+
+examples = ['0.png']
+
+def find_layout(image):
+    save_folder = './output'
+    # img = cv2.imread(image)
+    img = np.array(image)
+    result = table_engine(img)
+    save_structure_res(result, save_folder, os.path.basename("result").split('.')[0])
+
+    final_text = []
+    for line in result:
+        line.pop('img')
+        print(line)
+        final_text.append(line)
+
+    h, w, _ = img.shape
+    res = sorted_layout_boxes(result, w)
+    convert_info_docx(img, res, save_folder, os.path.basename("result").split('.')[0])
+
+    return final_text
+
+iface = gr.Interface(fn=find_layout, inputs=[gr.Image(type="pil")], outputs="text", examples=examples)
+iface.launch()

output/.result

@@ -0,0 +1 @@
+# nothing here

requirements.txt

@@ -0,0 +1,2 @@
+paddlepaddle
+paddleocr