ocr detection failed in some rows..

[tzktok]

问题描述 / Problem Description

my code

ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to download and load model into memory
img_path = 'test12.png'
result = ocr.ocr(img_path, cls=True)
for idx in range(len(result)):
    res = result[idx]
    for line in res:
        print(line)


# draw result
from PIL import Image
result = result[0]
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='Arial.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')

the result i get...

some rows not been detected..whats the reason @ZeyuChen @wencan @tink2123

运行环境 / Runtime Environment

• OS: ubuntu
• Paddle: latest
• PaddleOCR: latest

[GreatV]

try using another powerful model

[tzktok]

which model ? @GreatV