search

avinabsaha / ReIQA

Official implementation for CVPR2023 Paper "Re-IQA : Unsupervised Learning for Image Quality Assessment in the Wild"
https://arxiv.org/abs/2304.00451
MIT License
87 stars 7 forks source link

could you provide an example of test code with a trained model? #8

Open Tonsty opened 9 months ago

Tonsty commented 9 months ago

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 provided)

avinabsaha commented 9 months ago

Please use demo_content_aware_feats.py and demo_content_quality_aware_feats.py and merge the features to obtain final ReIQA features (8192 length) for any image! Typically, for IQA/VQA tasks, we develop feature extractors that can be calibrated on any domain specific quality dataset.

Tonsty commented 8 months ago

Thanks for your reply! I have got the feature exatror demo code and model file, but could you provide the regressor head code and model that predict the final quality score?