ReIQA
ReIQA copied to clipboard
Official implementation for CVPR2023 Paper "Re-IQA : Unsupervised Learning for Image Quality Assessment in the Wild"
Thanks for sharing your very interesting work! I have encountered an installation issue from requirements.txt: ``` ERROR: No matching distribution found for sklearn==1.1.3 ``` Changing sklearn==1.1.3 to scikit-learn==1.1.3, solved it....
Hi, thanks for your sharing of the code. I found the test_options.py in the current code, but I cannot find a test code with a trained model (only training code...
The process of determining "different-quality" after completing the swap between chunkc1 and chunkc2 is not very clear.
Is there any parameter setting information about the training of the regressors? I didn't get that good performance using a single-layer MLP regression score
Hi thank you for your work. I wonder if there is a model to get the final scores instead of the features? Thank you!