CLIP-IQA
CLIP-IQA copied to clipboard
A question encountered in clipiqa_single_image_demo.py
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]]