fix bugs

app.py

@@ -1,4 +1,3 @@
-
 import streamlit as st
 from PIL import Image
 import os
@@ -10,7 +9,6 @@ from pdf2image import convert_from_bytes
 #from st_btn_group import st_btn_group
 #from streamlit_option_menu import option_menu
 import docx
-from docx.shared import Pt
 from io import BytesIO  
 #import streamlit.components.v1 as components
 import base64
@@ -118,12 +116,12 @@ col1, col2 = st.columns(2)
 #    return image, result 
 import time
 
-max_page = 100
+max_page = 5
 def recognize_page_image(image):
     start = time.time()
     result = [[0,"Sample 1"],[1,"Sample 2"]]
-    result = reader.readtext(np.array(image), paragraph=False)
-    result = get_paragraph(result)
+    result = reader.readtext(np.array(image), batch_size=64, paragraph=False, y_ths=0, width_ths = 0)
+    result = get_paragraph(result, y_ths=0, x_ths = 0)
     end = time.time()
     return result,(end-start)
 
@@ -164,7 +162,7 @@ def process_pdf(uploaded_file):
     button_group.write(button_group_html,unsafe_allow_html=True)
     #col1.write("</div>",unsafe_allow_html=True)
     progress_bar.progress(0.99,text=f'{min(total_pages,max_page)} бет жүктелді')
-    
+
 def get_paragraph(raw_result, x_ths=1, y_ths=0.5, mode = 'ltr'):
     # create basic attributes
     box_group = []
@@ -188,18 +186,24 @@ def get_paragraph(raw_result, x_ths=1, y_ths=0.5, mode = 'ltr'):
         else:
             current_box_group = [box for box in box_group if box[7]==current_group]
             mean_height = np.mean([box[5] for box in current_box_group])
-            min_gx = min([box[1] for box in current_box_group]) - x_ths*mean_height
-            max_gx = max([box[2] for box in current_box_group]) + x_ths*mean_height
-            min_gy = min([box[3] for box in current_box_group]) - y_ths*mean_height
-            max_gy = max([box[4] for box in current_box_group]) + y_ths*mean_height
+            # min_gx = min([box[1] for box in current_box_group]) - x_ths*mean_height
+            # max_gx = max([box[2] for box in current_box_group]) + x_ths*mean_height
+            # min_gy = min([box[3] for box in current_box_group]) - y_ths*mean_height
+            # max_gy = max([box[4] for box in current_box_group]) + y_ths*mean_height
             add_box = False
-            for box in box_group0:
-                same_horizontal_level = (min_gx<=box[1]<=max_gx) or (min_gx<=box[2]<=max_gx)
-                same_vertical_level = (min_gy<=box[3]<=max_gy) or (min_gy<=box[4]<=max_gy)
-                if same_horizontal_level and same_vertical_level:
-                    box[7] = current_group
-                    add_box = True
-                    break
+
+            for box in current_box_group:
+                min_gx = box[1] - x_ths*mean_height
+                max_gx = box[2] + x_ths*mean_height
+                min_gy = box[3] - y_ths*mean_height
+                max_gy = box[4] + y_ths*mean_height
+                for box in box_group0:
+                    same_horizontal_level = (min_gx<=box[1]<=max_gx) or (min_gx<=box[2]<=max_gx)
+                    same_vertical_level = (min_gy<=box[6]<=max_gy)
+                    if same_horizontal_level and same_vertical_level:
+                        box[7] = current_group
+                        add_box = True
+                        break
             # cannot add more box, go to next group
             if add_box==False:
                 current_group += 1
@@ -233,6 +237,7 @@ def get_paragraph(raw_result, x_ths=1, y_ths=0.5, mode = 'ltr'):
 
     return result
 
+
 if uploaded_file is not None:
     if uploaded_file.type == "application/pdf":
         placeholder = col2.empty()
@@ -247,9 +252,9 @@ if uploaded_file is not None:
             image = Image.open(uploaded_file)
             #with open(os.path.join("tempDir",image_file))
             col1.image(image)
-            result = reader.readtext(np.array(image), paragraph=True)
+            result = reader.readtext(np.array(image), batch_size=64, paragraph=False, y_ths=0, width_ths = 0)
+            result = get_paragraph(result, y_ths=0)
             result_text = "\n\n".join([item[1] for item in result])
             button_group_html = generateButtonGroup(result)
             col2.write(button_group_html, unsafe_allow_html=True)
-            col2.markdown(result_text)
-        
+            col2.markdown(result_text)

models/best_norm_ED.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a93677c37a1bc9a268eb362df2772fbc9a5237b375740254e63063be2cebf6a4
+oid sha256:a0a93dd748a84d3998efccee420e3cabdf6b1693d3411374e871bcdb8c078169
 size 15217067