search

THUDM / ImageReward

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
Apache License 2.0
1.19k stars 65 forks source link

Training loss？ #106

Closed wzczc closed 1 week ago

wzczc commented 1 week ago

Thanks for your great work！But I have some questions about the training loss in the code. The paper mentions thr ranking loss: image but the code uses cross-entropy loss. image Are these two the same, or do they have similar optimization objectives?