Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleOCR into fixocr

doc/doc_ch/detection.md

@@ -23,7 +23,7 @@ wget -P ./train_data/  https://paddleocr.bj.bcebos.com/dataset/test_icdar2015_la
   └─ test_icdar2015_label.txt     icdar数据集的测试标注
 ```
 
-提供的标注文件格式为：
+提供的标注文件格式为，其中中间是"\t"分隔：
 ```
 " 图像文件名                    json.dumps编码的图像标注信息"
 ch4_test_images/img_61.jpg    [{"transcription": "MASA", "points": [[310, 104], [416, 141], [418, 216], [312, 179]], ...}]

tools/infer/predict_system.py

@@ -30,6 +30,7 @@ import time
 from ppocr.utils.utility import get_image_file_list
 from PIL import Image
 from tools.infer.utility import draw_ocr
+from tools.infer.utility import draw_ocr_box_txt
 
 
 class TextSystem(object):

tools/infer/utility.py

@@ -157,6 +157,44 @@ def draw_ocr(image, boxes, txts, scores, draw_txt=True, drop_score=0.5):
     return image
 
 
+def draw_ocr_box_txt(image, boxes, txts):
+    h, w = image.height, image.width
+    img_left = image.copy()
+    img_right = Image.new('RGB', (w, h), (255, 255, 255))
+
+    import random
+    # 每次使用相同的随机种子 ，可以保证两次颜色一致
+    random.seed(0)
+    draw_left = ImageDraw.Draw(img_left)
+    draw_right = ImageDraw.Draw(img_right)
+    for (box, txt) in zip(boxes, txts):
+        color = (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255))
+        draw_left.polygon(box, fill=color)
+        draw_right.polygon([box[0][0], box[0][1],
+                            box[1][0], box[1][1],
+                            box[2][0], box[2][1],
+                            box[3][0], box[3][1]], outline=color)
+        box_height = math.sqrt((box[0][0] - box[3][0]) ** 2 + (box[0][1] - box[3][1]) ** 2)
+        box_width = math.sqrt((box[0][0] - box[1][0]) ** 2 + (box[0][1] - box[1][1]) ** 2)
+        if box_height > 2 * box_width:
+            font_size = max(int(box_width * 0.9), 10)
+            font = ImageFont.truetype("./doc/simfang.ttf", font_size, encoding="utf-8")
+            cur_y = box[0][1]
+            for c in txt:
+                char_size = font.getsize(c)
+                draw_right.text((box[0][0] + 3, cur_y), c, fill=(0, 0, 0), font=font)
+                cur_y += char_size[1]
+        else:
+            font_size = max(int(box_height * 0.8), 10)
+            font = ImageFont.truetype("./doc/simfang.ttf", font_size, encoding="utf-8")
+            draw_right.text([box[0][0], box[0][1]], txt, fill=(0, 0, 0), font=font)
+    img_left = Image.blend(image, img_left, 0.5)
+    img_show = Image.new('RGB', (w * 2, h), (255, 255, 255))
+    img_show.paste(img_left, (0, 0, w, h))
+    img_show.paste(img_right, (w, 0, w * 2, h))
+    return np.array(img_show)
+
+
 def str_count(s):
     """
     Count the number of Chinese characters,

tools/program.py

@@ -114,7 +114,10 @@ def merge_config(config):
                 global_config[key] = value
         else:
             sub_keys = key.split('.')
-            assert (sub_keys[0] in global_config), "the sub_keys can only be one of global_config: {}, but get: {}, please check your running command".format(global_config.keys(), sub_keys[0])
+            assert (
+                sub_keys[0] in global_config
+            ), "the sub_keys can only be one of global_config: {}, but get: {}, please check your running command".format(
+                global_config.keys(), sub_keys[0])
             cur = global_config[sub_keys[0]]
             for idx, sub_key in enumerate(sub_keys[1:]):
                 assert (sub_key in cur)
@@ -177,7 +180,6 @@ def build(config, main_prog, startup_prog, mode):
                 optimizer.minimize(opt_loss)
                 opt_loss_name = opt_loss.name
                 global_lr = optimizer._global_learning_rate()
-                global_lr.persistable = True
                 fetch_name_list.insert(0, "lr")
                 fetch_varname_list.insert(0, global_lr.name)
     return (dataloader, fetch_name_list, fetch_varname_list, opt_loss_name)