compat_pillow (#10596)

applications/PCB字符识别/gen_data/gen.py

@@ -17,6 +17,7 @@ https://github.com/zcswdt/Color_OCR_image_generator
 """
 import os
 import random
+import PIL
 from PIL import Image, ImageDraw, ImageFont
 import json
 import argparse
@@ -55,8 +56,11 @@ def get_horizontal_text_picture(image_file, chars, fonts_list, cf):
     ch_w = []
     ch_h = []
     for ch in chars:
-        left, top, right, bottom = font.getbbox(ch)
-        wt, ht = right - left, bottom - top
+        if int(PIL.__version__.split('.')[0]) < 10:
+            wt, ht = font.getsize(ch)
+        else:
+            left, top, right, bottom = font.getbbox(ch)
+            wt, ht = right - left, bottom - top
         ch_w.append(wt)
         ch_h.append(ht)
     f_w = sum(ch_w)
@@ -102,8 +106,11 @@ def get_vertical_text_picture(image_file, chars, fonts_list, cf):
     ch_w = []
     ch_h = []
     for ch in chars:
-        left, top, right, bottom = font.getbbox(ch)
-        wt, ht = right - left, bottom - top
+        if int(PIL.__version__.split('.')[0]) < 10:
+            wt, ht = font.getsize(ch)
+        else:
+            left, top, right, bottom = font.getbbox(ch)
+            wt, ht = right - left, bottom - top
         ch_w.append(wt)
         ch_h.append(ht)
     f_w = max(ch_w)

ppocr/data/imaug/rec_img_aug.py

@@ -18,6 +18,7 @@ import numpy as np
 import random
 import copy
 from PIL import Image
+import PIL
 from .text_image_aug import tia_perspective, tia_stretch, tia_distort
 from .abinet_aug import CVGeometry, CVDeterioration, CVColorJitter, SVTRGeometry, SVTRDeterioration
 from paddle.vision.transforms import Compose
@@ -406,7 +407,7 @@ class GrayRecResizeImg(object):
     def __init__(self,
                  image_shape,
                  resize_type,
-                 inter_type='Image.LANCZOS',
+                 inter_type="Image.Resampling.LANCZOS",
                  scale=True,
                  padding=False,
                  **kwargs):

ppocr/utils/visual.py

@@ -14,6 +14,7 @@
 import cv2
 import os
 import numpy as np
+import PIL
 from PIL import Image, ImageDraw, ImageFont
 
 
@@ -62,8 +63,13 @@ def draw_box_txt(bbox, text, draw, font, font_size, color):
     draw.rectangle(bbox, fill=color)
 
     # draw ocr results
-    left, top, right, bottom = font.getbbox(text)
-    tw, th = right - left, bottom - top
+    if int(PIL.__version__.split('.')[0]) < 10:
+        tw = font.getsize(text)[0]
+        th = font.getsize(text)[1]
+    else:
+        left, top, right, bottom = font.getbbox(text)
+        tw, th = right - left, bottom - top
+    
     start_y = max(0, bbox[0][1] - th)
     draw.rectangle(
         [(bbox[0][0] + 1, start_y), (bbox[0][0] + tw + 1, start_y + th)],

ppstructure/utility.py

@@ -13,6 +13,7 @@
 # limitations under the License.
 import random
 import ast
+import PIL
 from PIL import Image, ImageDraw, ImageFont
 import numpy as np
 <<<<<<< HEAD
@@ -137,8 +138,13 @@ def draw_structure_result(image, result, font_path):
             [(box_layout[0], box_layout[1]), (box_layout[2], box_layout[3])],
             outline=box_color,
             width=3)
-        left, top, right, bottom = font.getbbox(region['type'])
-        text_w, text_h = right - left, bottom - top
+        
+        if int(PIL.__version__.split('.')[0]) < 10:
+            text_w, text_h = font.getsize(region['type'])
+        else:
+            left, top, right, bottom = font.getbbox(region['type'])
+            text_w, text_h = right - left, bottom - top
+
         draw_layout.rectangle(
             [(box_layout[0], box_layout[1]),
              (box_layout[0] + text_w, box_layout[1] + text_h)],

requirements.txt

@@ -15,4 +15,4 @@ premailer
 openpyxl
 attrdict
 PyMuPDF<1.21.0
-Pillow>=10.0.0
+Pillow

tools/infer/predict_rec.py

@@ -158,7 +158,7 @@ class TextRecognizer(object):
             if self.rec_algorithm == 'ViTSTR':
                 img = image_pil.resize([imgW, imgH], Image.BICUBIC)
             else:
-                img = image_pil.resize([imgW, imgH], Image.LANCZOS)
+                img = image_pil.resize([imgW, imgH], Image.Resampling.LANCZOS)
             img = np.array(img)
             norm_img = np.expand_dims(img, -1)
             norm_img = norm_img.transpose((2, 0, 1))

tools/infer/utility.py

@@ -19,6 +19,7 @@ import platform
 import cv2
 import numpy as np
 import paddle
+import PIL
 from PIL import Image, ImageDraw, ImageFont
 import math
 from paddle import inference
@@ -475,7 +476,11 @@ def draw_box_txt_fine(img_size, box, txt, font_path="./doc/fonts/simfang.ttf"):
 def create_font(txt, sz, font_path="./doc/fonts/simfang.ttf"):
     font_size = int(sz[1] * 0.99)
     font = ImageFont.truetype(font_path, font_size, encoding="utf-8")
-    length = font.getlength(txt)
+    if int(PIL.__version__.split('.')[0]) < 10:
+        length = font.getsize(txt)[0]
+    else:
+        length = font.getlength(txt)
+    
     if length > sz[0]:
         font_size = int(font_size * sz[0] / length)
         font = ImageFont.truetype(font_path, font_size, encoding="utf-8")