Pavan Chennagiri

The code should work in either case. Please ensure all the dependencies are installed in their correct versions. Distributed training can be done multiple ways in PyTorch. The code which...

That will be created by the program. Make sure there does not exist 'sharedfile' file in your working directory before running. The program will fail if there is already a...

Currently we haven't conducted experiments which involve supervised finetuning of the CONTRIQUE encoder since our focus in this work was on unsupervised pretraining. We might conduct this experiment in the...

The link seems to working for me http://database.mmsp-kn.de/kadid-10k-database.html The link seems to be not secure (https), try accessing with just http

I need more details on what exactly you are experimenting. Are you trying to fine tune the model using ground truth quality scores? Or your data is different and using...

In my current implementation the ridge regression is trained on the entire dataset in one shot (not in batches). Note that I don't combine multiple IQA datasets for training ridge...

The data we used to train the model is from different public datasets and we have listed the names of those datasets in the paper. During testing please make sure...

> I wonder what the answer of the test.py is? I get: 0.19145732 as the answer in the test example. Is that the correct answer? The gold standard way to...

> However, I note that if I convert the bmp images to png, I get a different answer. Is this correct? Do all files only need to be .bmp? How...

I am currently out of town. I will verify these observations once I am back. Thanks for pointing this!