search

IceClear / CLIP-IQA

[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images
Other
344 stars 20 forks source link

How do I train my own data set？ #21

Open Joey1224 opened 8 months ago

Joey1224 commented 8 months ago

HI~ Thank you for your work！ I want to train a model that recognizes cars and boats, is the train config and CSV file labeled correctly?

config csv
IceClear commented 8 months ago

Hi. Our model is for image quality assessment rather than classification. So I am not sure if it is suitable to directly training it for your case. Our output is multiplied by 100. So you may need to rescale it to [0,1] before calculating the loss.