Jianyi Wang comments

Results 157 comments of


                                            Jianyi Wang

Only return single attribute value for inferencing single image demo

Hi. Thanks for your interest in our work. For different attributes, they are actually different attribute pairs. You only need to change the classname in the config file: [here](https://github.com/IceClear/CLIP-IQA/blob/main/configs/clipiqa/clipiqa_attribute_test.py#L16). I...

Only return single attribute value for inferencing single image demo

Hi. We do not need training on assessing these attributes. Just CLIP model is required.

Only return single attribute value for inferencing single image demo

> Thanks for your reply. How can I set the appropriate model setting for attributes values [Brightness', 'Sharpness', 'Noisiness', 'Colorfulness', and 'Contrast']? I got mismatch error for model and loaded...

Only return single attribute value for inferencing single image demo

You loaded the wrong model. The model is for CLIPIQA+ (CLIPIQAPredictor). You do not need to load any model for testing CLIPIQA (CLIPIQAFixed).

Only return single attribute value for inferencing single image demo

Hi. Sry that I am busy with other works so far. May do it when I am available later, possibly after CVPR submission.

evaluate() got an unexpected keyword argument 'gpu_collect' while training clipiqa_coop_koniq

I did not meet such a problem. It seems that you are not using the right env. You may switch to another repo for test. See #13

Image transformation methods

![image](https://github.com/IceClear/CLIP-IQA/assets/22350795/3b1abddd-7f6d-434f-8b2a-ab204f527fdf)

Image transformation methods

> Well this part still does not clarify which type of image transformation being used in the code and only mentioned the train and test splitting. Are you suggesting that...

About dataset setting.

Hi. We did not use Koniq-valid. We just directly used the latest ckpt for test.