IceClear/CLIP-IQA

The same picture scores different times.What's the situation? Is it my setting wrong?

hjb25286 opened this issue · 0 comments

hjb25286 commented

(clipiqa) root@SH-JC-3F-6R-1A:/home/hu/Super_Resolution/CLIP-IQA-2-3.8/demo# python clipiqa_single_image_demo.py
Initializing a generic context
Initial context: "X X X X X X X X X X X X X X X X"
Number of context words (tokens): 16

[0.17663574]
(clipiqa) root@SH-JC-3F-6R-1A:/home/hu/Super_Resolution/CLIP-IQA-2-3.8/demo# python clipiqa_single_image_demo.py
Initializing a generic context
Initial context: "X X X X X X X X X X X X X X X X"
Number of context words (tokens): 16

[0.51953125]
(clipiqa) root@SH-JC-3F-6R-1A:/home/hu/Super_Resolution/CLIP-IQA-2-3.8/demo# python clipiqa_single_image_demo.py
Initializing a generic context
Initial context: "X X X X X X X X X X X X X X X X"
Number of context words (tokens): 16

[0.79296875]
(clipiqa) root@SH-JC-3F-6R-1A:/home/hu/Super_Resolution/CLIP-IQA-2-3.8/demo# python clipiqa_single_image_demo.py
Initializing a generic context
Initial context: "X X X X X X X X X X X X X X X X"
Number of context words (tokens): 16

[0.32763672]