tifa-benchmark
/

promptcap-coco-vqa

visual-question-answering

image-captioning

Model card Files Files and versions

yushihu commited on Jan 25, 2023

Commit

a094e0c

·

1 Parent(s): 5eb3f77

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -27,7 +27,8 @@ pip install promptcap
 ## Captioning Pipeline
 Please follow the prompt format, which will give the best performance.
-Generate a prompt-guided caption by following
 ```python
 import torch
 from promptcap import PromptCap
@@ -85,7 +86,7 @@ question = "what year was this taken?"
 image = "dvds.jpg"
 ocr = "yip AE Mht juor 02/14/2012"
-print(vqa_model.vqa(prompt, image, ocr=ocr))
 ```
 Because of the flexibility of Unifiedqa, PromptCap also supports multiple-choice VQA

 ## Captioning Pipeline
 Please follow the prompt format, which will give the best performance.
+Generate a prompt-guided caption by following:
 ```python
 import torch
 from promptcap import PromptCap
 image = "dvds.jpg"
 ocr = "yip AE Mht juor 02/14/2012"
+print(vqa_model.vqa(question, image, ocr=ocr))
 ```
 Because of the flexibility of Unifiedqa, PromptCap also supports multiple-choice VQA