Update models

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.TTF filter=lfs diff=lfs merge=lfs -text
 images/car_plate.jpeg filter=lfs diff=lfs merge=lfs -text
+*.ttc filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,87 +1,19 @@
 # -*- encoding: utf-8 -*-
-import math
-import random
 import time
 from pathlib import Path
 
 import cv2
 import gradio as gr
-import numpy as np
-from PIL import Image, ImageDraw, ImageFont
 from rapidocr_onnxruntime import RapidOCR
 
+from utils import visualize
 
-def draw_ocr_box_txt(image, boxes, txts, font_path,
- scores=None, text_score=0.5):
- h, w = image.height, image.width
- img_left = image.copy()
- img_right = Image.new('RGB', (w, h), (255, 255, 255))
-
- random.seed(0)
- draw_left = ImageDraw.Draw(img_left)
- draw_right = ImageDraw.Draw(img_right)
- for idx, (box, txt) in enumerate(zip(boxes, txts)):
- if scores is not None and float(scores[idx]) < text_score:
- continue
-
- color = (random.randint(0, 255),
- random.randint(0, 255),
- random.randint(0, 255))
-
- box = [tuple(v) for v in box]
- 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(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)
- 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)
-
- 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 visualize(image_path, boxes, txts, scores,
- font_path="./FZYTK.TTF"):
- image = Image.open(image_path)
-
- draw_img = draw_ocr_box_txt(image, boxes,
- txts, font_path,
- scores,
- text_score=0.5)
-
- draw_img_save = Path("./inference_results/")
- if not draw_img_save.exists():
- draw_img_save.mkdir(parents=True, exist_ok=True)
-
- time_stamp = time.strftime('%Y-%m-%d-%H-%M-%S', time.localtime(time.time()))
- image_save = str(draw_img_save / f'{time_stamp}_{Path(image_path).name}')
- cv2.imwrite(image_save, draw_img[:, :, ::-1])
- return image_save
+font_dict = {
+ 'ch': 'FZYTK.TTF',
+ 'japan': 'japan.ttc',
+ 'korean': 'korean.ttf',
+ 'en': 'FZYTK.TTF'
+}
 
 
 def inference(img_path, box_thresh=0.5, unclip_ratio=1.6, text_score=0.5,
@@ -102,8 +34,17 @@ def inference(img_path, box_thresh=0.5, unclip_ratio=1.6, text_score=0.5,
  rec_img_shape=rec_image_shape)
  elapse = time.time() - s
 
+ if 'ch' in rec_model_path or 'en' in rec_model_path:
+ lan_name = 'ch'
+ elif 'japan' in rec_model_path:
+ lan_name = 'japan'
+ elif 'korean' in rec_model_path:
+ lan_name = 'korean'
+ else:
+ lan_name = 'ch'
+
  out_log_list.append(f'Init Model cost: {elapse:.5f}')
- out_log_list.extend([f'det_model:{det_model_path}',
+ out_log_list.extend([f'det_model: {det_model_path}',
  f'rec_model: {rec_model_path}',
  f'rec_image_shape: {rec_image_shape}'])
 
@@ -120,73 +61,78 @@ def inference(img_path, box_thresh=0.5, unclip_ratio=1.6, text_score=0.5,
  return img_path, '未识别到有效文本', out_log
 
  dt_boxes, rec_res, scores = list(zip(*ocr_result))
- img_save_path = visualize(img_path, dt_boxes, rec_res, scores)
+ font_path = Path('fonts') / font_dict.get(lan_name)
+ img_save_path = visualize(img_path, dt_boxes, rec_res, scores,
+ font_path=str(font_path))
  output_text = [f'{one_rec} {float(score):.4f}'
  for one_rec, score in zip(rec_res, scores)]
  return img_save_path, output_text, out_log
 
 
-examples = [['images/1.jpg'], 
- ['images/ch_en_num.jpg'], 
- ['images/air_ticket.jpg'], 
- ['images/car_plate.jpeg'], 
- ['images/idcard.jpg'], 
- ['images/train_ticket.jpeg']]
-
-with gr.Blocks(title='RapidOCR') as demo:
- gr.Markdown("""
- <h1><center><a href="https://github.com/RapidAI/RapidOCR" target="_blank">Rapid⚡OCR</a></center></h1>
-
- ### Docs: [Docs](https://rapidocr.rtfd.io/)
- ### Parameters docs: [link](https://github.com/RapidAI/RapidOCR/tree/main/python#configyaml%E4%B8%AD%E5%B8%B8%E7%94%A8%E5%8F%82%E6%95%B0%E4%BB%8B%E7%BB%8D)
- - **box_thresh**: 检测到的框是文本的概率，值越大，框中是文本的概率就越大。存在漏检时，调低该值。取值范围：[0, 1.0]
- - **unclip_ratio**: 控制文本检测框的大小，值越大，检测框整体越大。在出现框截断文字的情况，调大该值。取值范围：[1.5, 2.0]
- - **text_score**: 文本识别结果是正确的置信度，值越大，显示出的识别结果更准确。存在漏检时，调低该值。取值范围：[0, 1.0]
- ### 运行环境：
- Python: 3.8 | onnxruntime: 1.14.1 | rapidocr_onnxruntime: 1.2.5""")
- gr.Markdown('**超参数调节**')
- with gr.Row():
- box_thresh = gr.Slider(minimum=0, maximum=1.0, value=0.5,
- label='box_thresh', step=0.1,
- interactive=True,
- info='[0, 1.0]')
- unclip_ratio = gr.Slider(minimum=1.5, maximum=2.0, value=1.6,
- label='unclip_ratio', step=0.1,
- interactive=True,
- info='[1.5, 2.0]')
- text_score = gr.Slider(minimum=0, maximum=1.0, value=0.5,
- label='text_score', step=0.1,
- interactive=True,
- info='[0, 1.0]')
-
- gr.Markdown('**模型选择**')
- with gr.Row():
- text_det = gr.Dropdown(['ch_PP-OCRv3_det_infer.onnx',
- 'ch_PP-OCRv2_det_infer.onnx',
- 'ch_ppocr_server_v2.0_det_infer.onnx'],
- label='选择文本检测模型',
- value='ch_PP-OCRv3_det_infer.onnx',
- interactive=True)
-
- text_rec = gr.Dropdown(['ch_PP-OCRv3_rec_infer.onnx',
- 'ch_PP-OCRv2_rec_infer.onnx',
- 'ch_ppocr_server_v2.0_rec_infer.onnx'],
- label='选择文本识别模型',
- value='ch_PP-OCRv3_rec_infer.onnx',
- interactive=True)
-
- with gr.Row():
- input_img = gr.Image(type='filepath', label='Input')
- out_img = gr.Image(type='filepath', label='Output')
- out_log = gr.outputs.Textbox(type='text', label='Run Log')
- out_txt = gr.outputs.Textbox(type='text', label='RecText')
- button = gr.Button('Submit')
- button.click(fn=inference,
- inputs=[input_img, box_thresh, unclip_ratio, text_score,
- text_det, text_rec],
- outputs=[out_img, out_txt, out_log])
- gr.Examples(examples=examples,
- inputs=[input_img, box_thresh, unclip_ratio, text_score,
- text_det, text_rec],
- outputs=[out_img, out_txt, out_log], fn=inference)
-demo.launch(debug=True, enable_queue=True)
+if __name__ == '__main__':
+
+ examples = [['images/1.jpg'],
+ ['images/ch_en_num.jpg'],
+ ['images/air_ticket.jpg'],
+ ['images/car_plate.jpeg'],
+ ['images/idcard.jpg'],
+ ['images/train_ticket.jpeg'],
+ ['images/japan_2.jpg'],
+ ['images/korean_1.jpg']]
+
+ with gr.Blocks(title='RapidOCR') as demo:
+ gr.Markdown("""
+ <h1><center><a href="https://github.com/RapidAI/RapidOCR" target="_blank">Rapid⚡OCR</a></center></h1>
+
+ ### Docs: [Docs](https://rapidocr.rtfd.io/)
+ ### 运行环境：
+ Python: 3.8 | onnxruntime: 1.14.1 | rapidocr_onnxruntime: 1.2.5""")
+ gr.Markdown(
+ '''**[超参数调节](https://github.com/RapidAI/RapidOCR/tree/main/python#configyaml%E4%B8%AD%E5%B8%B8%E7%94%A8%E5%8F%82%E6%95%B0%E4%BB%8B%E7%BB%8D)**
+ - **box_thresh**: 检测到的框是文本的概率，值越大，框中是文本的概率就越大。存在漏检时，调低该值。取值范围：[0, 1.0]
+ - **unclip_ratio**: 控制文本检测框的大小，值越大，检测框整体越大。在出现框截断文字的情况，调大该值。取值范围：[1.5, 2.0]
+ - **text_score**: 文本识别结果是正确的置信度，值越大，显示出的识别结果更准确。存在漏检时，调低该值。取值范围：[0, 1.0]
+ ''')
+ with gr.Row():
+ box_thresh = gr.Slider(minimum=0, maximum=1.0, value=0.5,
+ label='box_thresh', step=0.1,
+ interactive=True,
+ info='[0, 1.0]')
+ unclip_ratio = gr.Slider(minimum=1.5, maximum=2.0, value=1.6,
+ label='unclip_ratio', step=0.1,
+ interactive=True,
+ info='[1.5, 2.0]')
+ text_score = gr.Slider(minimum=0, maximum=1.0, value=0.5,
+ label='text_score', step=0.1,
+ interactive=True,
+ info='[0, 1.0]')
+
+ gr.Markdown('**[模型选择](https://github.com/RapidAI/RapidOCR/blob/main/docs/models.md)**')
+ with gr.Row():
+ text_det = gr.Dropdown(['ch_PP-OCRv3_det_infer.onnx',
+ 'ch_PP-OCRv2_det_infer.onnx',
+ 'ch_ppocr_server_v2.0_det_infer.onnx'],
+ label='选择文本检测模型',
+ value='ch_PP-OCRv3_det_infer.onnx',
+ interactive=True)
+ rec_model_list = [v.name for v in Path('models/text_rec').iterdir()]
+ text_rec = gr.Dropdown(rec_model_list,
+ label='选择文本识别模型(包括中英文和多语言)',
+ value='ch_PP-OCRv3_rec_infer.onnx',
+ interactive=True)
+
+ with gr.Row():
+ input_img = gr.Image(type='filepath', label='Input')
+ out_img = gr.Image(type='filepath', label='Output')
+ out_log = gr.outputs.Textbox(type='text', label='Run Log')
+ out_txt = gr.outputs.Textbox(type='text', label='RecText')
+ button = gr.Button('Submit')
+ button.click(fn=inference,
+ inputs=[input_img, box_thresh, unclip_ratio, text_score,
+ text_det, text_rec],
+ outputs=[out_img, out_txt, out_log])
+ gr.Examples(examples=examples,
+ inputs=[input_img, box_thresh, unclip_ratio, text_score,
+ text_det, text_rec],
+ outputs=[out_img, out_txt, out_log], fn=inference)
+ demo.launch(debug=True, enable_queue=True)

FZYTK.TTF → models/text_rec/en_PP-OCRv3_rec_infer.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4065a23df6823c8e2b69a0e76d02f02a6470b8774a5e91086609701ad95cc33f
-size 3241748
+oid sha256:ef7abd8bd3629ae57ea2c28b425c1bd258a871b93fd2fe7c433946ade9b5d9ea
+size 8967018

models/text_rec/en_number_mobile_v2.0_rec_infer.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e679ba625c544444be78292a50d9e1af9caa1569239a88bb8b864cb688b11c01
+size 1882607

models/text_rec/japan_rec_crnn_v2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0495059f5738166e606d864b04ff00093f67a807efb02cddf472839cae970c
+size 3571807

models/text_rec/korean_mobile_v2.0_rec_infer.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6558500138b43b46a4941957fb8c918546dae5fb0e71718536f1883acc80faf
+size 3290650