Skip to content

πŸ“„ Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.

Fix bugs of python inference

SWHL6acae1a88fd7
diff --git a/python/ch_ppocr_mobile_v2_cls/utils.py b/python/ch_ppocr_mobile_v2_cls/utils.py
index edbd6a2..6fd2865 100755
--- a/python/ch_ppocr_mobile_v2_cls/utils.py
+++ b/python/ch_ppocr_mobile_v2_cls/utils.py
@@ -19,7 +19,7 @@ import imghdr
def get_image_file_list(img_file):
imgs_lists = []
if img_file is None or not os.path.exists(img_file):
- raise ValueError("not found any img file in {}".format(img_file))
+ raise FileNotFoundError(f"not found any img file in {img_file}")
img_end = {'jpg', 'bmp', 'png', 'jpeg', 'rgb', 'tif', 'tiff', 'gif', 'GIF'}
if os.path.isfile(img_file) and imghdr.what(img_file) in img_end:
@@ -30,7 +30,7 @@ def get_image_file_list(img_file):
if os.path.isfile(file_path) and imghdr.what(file_path) in img_end:
imgs_lists.append(file_path)
if len(imgs_lists) == 0:
- raise ValueError("not found any img file in {}".format(img_file))
+ raise FileNotFoundError(f"not found any img file in {img_file}")
return imgs_lists
diff --git a/python/ch_ppocr_server_v2_det/utils.py b/python/ch_ppocr_server_v2_det/utils.py
index a3ac890..4ed6e55 100755
--- a/python/ch_ppocr_server_v2_det/utils.py
+++ b/python/ch_ppocr_server_v2_det/utils.py
@@ -314,7 +314,8 @@ class DBPostProcess(object):
bitmap = _bitmap
height, width = bitmap.shape
- outs = cv2.findContours((bitmap * 255).astype(np.uint8), cv2.RETR_LIST,
+ outs = cv2.findContours((bitmap * 255).astype(np.uint8),
+ cv2.RETR_LIST,
cv2.CHAIN_APPROX_SIMPLE)
if len(outs) == 3:
img, contours, _ = outs[0], outs[1], outs[2]
diff --git a/python/rapidOCR.py b/python/rapidOCR.py
index a75418e..8c09c04 100644
--- a/python/rapidOCR.py
+++ b/python/rapidOCR.py
@@ -87,33 +87,40 @@ def draw_ocr_box_txt(image, boxes, txts,
for idx, (box, txt) in enumerate(zip(boxes, txts)):
if scores is not None and scores[idx] < drop_score:
continue
- color = (random.randint(0, 255), random.randint(0, 255),
+
+ 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)
+ 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(font_path, font_size, encoding="utf-8")
+ font = ImageFont.truetype(font_path, 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)
+ 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(font_path, font_size, encoding="utf-8")
- draw_right.text(
- [box[0][0], box[0][1]], txt, fill=(0, 0, 0), font=font)
+ font = ImageFont.truetype(font_path, 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))
@@ -132,8 +139,7 @@ def visualize(image_path, boxes, rec_res):
draw_img_save = Path("./inference_results/")
if not draw_img_save.exists():
- draw_img_save.mkdir(parents=True,
- exist_ok=True)
+ draw_img_save.mkdir(parents=True, exist_ok=True)
image_save = str(draw_img_save / f'infer_{Path(image_path).name}')
cv2.imwrite(image_save, draw_img[:, :, ::-1])
@@ -220,16 +226,16 @@ class TextSystem(object):
dt_boxes, elapse = self.text_detector(img)
print("dt_boxes num : {}, elapse : {}".format(
len(dt_boxes), elapse))
- if dt_boxes is None:
+ if dt_boxes is None or len(dt_boxes) < 1:
return None, None
- img_crop_list = []
-
dt_boxes = self.sorted_boxes(dt_boxes)
+ img_crop_list = []
for bno in range(len(dt_boxes)):
tmp_box = copy.deepcopy(dt_boxes[bno])
img_crop = self.get_rotate_crop_image(img, tmp_box)
img_crop_list.append(img_crop)
+
if self.use_angle_cls:
img_crop_list, angle_list, elapse = self.text_classifier(
img_crop_list)
@@ -239,7 +245,7 @@ class TextSystem(object):
rec_res, elapse = self.text_recognizer(img_crop_list)
print("rec_res num : {}, elapse : {}".format(
len(rec_res), elapse))
- # self.print_draw_crop_rec_res(img_crop_list, rec_res)
+
filter_boxes, filter_rec_res = [], []
for box, rec_reuslt in zip(dt_boxes, rec_res):
text, score = rec_reuslt