Hugging Face's logo

tifa-benchmark
/
promptcap-coco-vqa

Image-to-Text
Transformers
PyTorch
English
ofa
visual-question-answering
image-captioning
Model card Files Community
2
yushihu commited on
Commit
a094e0c
•
1 Parent(s): 5eb3f77

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -27,7 +27,8 @@ pip install promptcap
27
  ## Captioning Pipeline
28
 
29
  Please follow the prompt format, which will give the best performance.
30
- Generate a prompt-guided caption by following
 
31
  ```python
32
  import torch
33
  from promptcap import PromptCap
@@ -85,7 +86,7 @@ question = "what year was this taken?"
85
  image = "dvds.jpg"
86
  ocr = "yip AE Mht juor 02/14/2012"
87
 
88
- print(vqa_model.vqa(prompt, image, ocr=ocr))
89
  ```
90
 
91
  Because of the flexibility of Unifiedqa, PromptCap also supports multiple-choice VQA
 
27
  ## Captioning Pipeline
28
 
29
  Please follow the prompt format, which will give the best performance.
30
+
31
+ Generate a prompt-guided caption by following:
32
  ```python
33
  import torch
34
  from promptcap import PromptCap
 
86
  image = "dvds.jpg"
87
  ocr = "yip AE Mht juor 02/14/2012"
88
 
89
+ print(vqa_model.vqa(question, image, ocr=ocr))
90
  ```
91
 
92
  Because of the flexibility of Unifiedqa, PromptCap also supports multiple-choice VQA