search

yunjey / stargan

StarGAN - Official PyTorch Implementation (CVPR 2018)
MIT License
5.23k stars 973 forks source link

Attributes in CelebA pre-trained model #101

Open JosephPai opened 5 years ago

JosephPai commented 5 years ago

Are all attributes in CelebA included in the pre-trained model?

Or just few of them?

'5_o_Clock_Shadow', 'Arched_Eyebrows', 'Attractive', 'Bags_Under_Eyes', 'Bald', 'Bangs', 'Big_Lips', 'Big_Nose', 'Black_Hair', 'Blond_Hair', 'Blurry', 'Brown_Hair', 'Bushy_Eyebrows', 'Chubby', 'Double_Chin', 'Eyeglasses', 'Goatee', 'Gray_Hair', 'Heavy_Makeup', 'High_Cheekbones', 'Male', 'Mouth_Slightly_Open', 'Mustache', 'Narrow_Eyes', 'No_Beard', 'Oval_Face', 'Pale_Skin', 'Pointy_Nose', 'Receding_Hairline', 'Rosy_Cheeks', 'Sideburns', 'Smiling', 'Straight_Hair', 'Wavy_Hair', 'Wearing_Earrings', 'Wearing_Hat', 'Wearing_Lipstick', 'Wearing_Necklace', 'Wearing_Necktie', 'Young'

rex-yue-wu commented 5 years ago

No. The author replied in #97. Only the used 5 attributes are supported. You have to retrain the model yourself for other attributes.

renmengyuan commented 3 years ago

No. The author replied in #97. Only the used 5 attributes are supported. You have to retrain the model yourself for other attributes.

Is there some idea about how to prepare the format of datasets if I only want to change the hairstyle?

futurianh1k commented 3 years ago

Dooray! 메일 발송 실패 안내

메일 발송 실패 안내

@.***) 님께 보낸 메일이 전송되지 못하였습니다.

      실패 사유를 확인해보세요.

        * 받는 사람 : 

@.***) 

        * 발송 시간 : 

2021-07-15T16:40:38

        * 메일 제목 : 

Re: [yunjey/stargan] Attributes in CelebA pre-trained model (#101)

            * 실패 사유 : 

받는 사람의 메일함 용량이 가득 찼습니다. 받는 사람에게 메일함 정리를 요청하신 후 다시 발송해 보세요.

      이 메일은 발신전용으로 회신되지 않습니다.
      더 궁금하신 사항은
      ***@***.***
      으로 문의해 주시기 바랍니다.

    © Dooray!.
kalikhademi commented 1 year ago

if the pre-trained model includes attribute Young, can I change young ones to old and old one to youngs or only young to old is supported?