Update README.md
Browse files
README.md
CHANGED
@@ -52,6 +52,10 @@ processor = AutoProcessor.from_pretrained(model_path)
|
|
52 |
url = "https://github.com/LLaVA-VL/blog/blob/main/2024-10-03-llava-critic/static/images/critic_img_seven.png?raw=True"
|
53 |
image = Image.open(requests.get(url, stream=True).raw)
|
54 |
|
|
|
|
|
|
|
|
|
55 |
prompt_text = ("Given a question and a reference image, please analyze in detail the two provided answers (Answer 1 and Answer 2). " \
|
56 |
"Evaluate them based on the following three core dimensions:\n" \
|
57 |
"1. Semantic accuracy: How well the answer reflects the visual content of the image\n" \
|
|
|
52 |
url = "https://github.com/LLaVA-VL/blog/blob/main/2024-10-03-llava-critic/static/images/critic_img_seven.png?raw=True"
|
53 |
image = Image.open(requests.get(url, stream=True).raw)
|
54 |
|
55 |
+
Query = 'What does this image present?'
|
56 |
+
R1 = 'The image is a black and white sketch of a line that appears to be in the shape of a cross. The line is a simple and straightforward representation of the cross shape, with two straight lines intersecting at a point.'
|
57 |
+
R2 = 'This is a handwritten number seven.'
|
58 |
+
|
59 |
prompt_text = ("Given a question and a reference image, please analyze in detail the two provided answers (Answer 1 and Answer 2). " \
|
60 |
"Evaluate them based on the following three core dimensions:\n" \
|
61 |
"1. Semantic accuracy: How well the answer reflects the visual content of the image\n" \
|