IceClear / CLIP-IQA

[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images
Other
315 stars 18 forks source link

A question encountered in clipiqa_single_image_demo.py #19

Open 904763189cy opened 11 months ago

904763189cy commented 11 months ago

After running this code:output, attributes = restoration_inference(model, os.path.join(args.file_path), return_attributes=True)

output and attributes are the same. Why return the same two data?

Code running result:

attributes>>>>>>>>>>>>>>>>>> tensor([[0.9644, 0.3345, 0.9995, 0.0357, 0.2766, 0.3577]]) output>>>>>>>>>>>>>>>>>> [[0.96435547 0.33447266 0.9995117 0.03567505 0.27661133 0.35766602]]