ReIQA
ReIQA copied to clipboard
Information for training regressors
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
I will try to have something on this soon.
Using sklearn's elasticNet with moderate hyper-parameter will be able to produce results reported in paper.
For exact results, need extensive hyper parameter optimization.
Where can I find the ground truth quality score for AVA(Aesthetic Visual Analysis) dataset?