Hugging Face's logo

stepfun-ai
/
GOT-OCR2_0

Image-Text-to-Text
Transformers
Safetensors
multilingual
GOT
feature-extraction
got
vision-language
ocr2.0
custom_code
Model card Files Community
32
ucaslcl commited on
Commit
3cac839
•
1 Parent(s): 64c8045

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -10
README.md CHANGED
@@ -7,9 +7,7 @@
7
  [Haoran Wei*](https://scholar.google.com/citations?user=J4naK0MAAAAJ&hl=en), Chenglong Liu*, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu, [Zheng Ge](https://joker316701882.github.io/), Liang Zhao, [Jianjian Sun](https://scholar.google.com/citations?user=MVZrGkYAAAAJ&hl=en), [Yuang Peng](https://scholar.google.com.hk/citations?user=J0ko04IAAAAJ&hl=zh-CN&oi=ao), Chunrui Han, [Xiangyu Zhang](https://scholar.google.com/citations?user=yuB-cfoAAAAJ&hl=en)
8
 
9
 
10
- <div style="display: flex; flex-direction: column; align-items: center;">
11
- <img src="https://github.com/Ucas-HaoranWei/GOT-OCR2.0/blob/main/assets/got_logo.png" alt="logo" style="margin-bottom: -20px;">
12
- </div>
13
 
14
 
15
 
@@ -38,19 +36,19 @@ image_file = 'xxx.jpg'
38
  model.chat(tokenizer, image_file, ocr_type='ocr')
39
 
40
  # format texts OCR:
41
- model.chat(tokenizer, image_file, ocr_type='format')
42
 
43
  # fine-grained OCR:
44
- model.chat(tokenizer, image_file, ocr_type='ocr', ocr_box='')
45
- model.chat(tokenizer, image_file, ocr_type='format', ocr_box='')
46
- model.chat(tokenizer, image_file, ocr_type='ocr', ocr_color='')
47
- model.chat(tokenizer, image_file, ocr_type='format', ocr_color='')
48
 
49
  # multi-crop OCR:
50
- res = model.chat_crop(tokenizer, image_file = image_file)
51
 
52
  # render the formatted OCR results:
53
- model.chat(tokenizer, image_file, ocr_type='format', ocr_box='', ocr_color='', render=True, save_render_file = './demo.html')
54
 
55
  print(res)
56
 
 
7
  [Haoran Wei*](https://scholar.google.com/citations?user=J4naK0MAAAAJ&hl=en), Chenglong Liu*, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu, [Zheng Ge](https://joker316701882.github.io/), Liang Zhao, [Jianjian Sun](https://scholar.google.com/citations?user=MVZrGkYAAAAJ&hl=en), [Yuang Peng](https://scholar.google.com.hk/citations?user=J0ko04IAAAAJ&hl=zh-CN&oi=ao), Chunrui Han, [Xiangyu Zhang](https://scholar.google.com/citations?user=yuB-cfoAAAAJ&hl=en)
8
 
9
 
10
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6653eee7a2d7a882a805ab95/dAOiYlj3Hdl4_G1KpahcB.png)
 
 
11
 
12
 
13
 
 
36
  model.chat(tokenizer, image_file, ocr_type='ocr')
37
 
38
  # format texts OCR:
39
+ # model.chat(tokenizer, image_file, ocr_type='format')
40
 
41
  # fine-grained OCR:
42
+ # model.chat(tokenizer, image_file, ocr_type='ocr', ocr_box='')
43
+ # model.chat(tokenizer, image_file, ocr_type='format', ocr_box='')
44
+ # model.chat(tokenizer, image_file, ocr_type='ocr', ocr_color='')
45
+ # model.chat(tokenizer, image_file, ocr_type='format', ocr_color='')
46
 
47
  # multi-crop OCR:
48
+ # res = model.chat_crop(tokenizer, image_file = image_file)
49
 
50
  # render the formatted OCR results:
51
+ # model.chat(tokenizer, image_file, ocr_type='format', ocr_box='', ocr_color='', render=True, save_render_file = './demo.html')
52
 
53
  print(res)
54