deepinsight
Has anyone tried training Arcface with only open license databases?
I want train a model that can be used for commercial purposes. So I was wondering if training it with open license databases like WebFace42M and Glint360K would result in a model with good accuracy. Has anyone tried it? What databases did you end up using?
Hello,
Those datasets are not open license, they are used for non-commercial purposes only. We trained with our internal datasets of around ~50M images and got very good accuracy (Top 5 In NIST). We did some changes to ARCFace loss and additional augmentation strategies. So, yes, it is possible to obtain good models with this repo.
Thanks for clarifying @mlourencoeb, I read that these databases were open-source in the training instructions and just assumed they are good for commercial use
Do you know of any commercial-use databases I can use to train Arcface to get decent accuracy? Doesn't have to be SOTA numbers but maybe a lot better than Facenet or some older models
Hello,
Those datasets are not open license, they are used for non-commercial purposes only. We trained with our internal datasets of around ~50M images and got very good accuracy (Top 5 In NIST). We did some changes to ARCFace loss and additional augmentation strategies. So, yes, it is possible to obtain good models with this repo.
Can you share what changes you made to ArcFace loss and the augmentation you used?
Hello,
Those datasets are not open license, they are used for non-commercial purposes only. We trained with our internal datasets of around ~50M images and got very good accuracy (Top 5 In NIST). We did some changes to ARCFace loss and additional augmentation strategies. So, yes, it is possible to obtain good models with this repo.
Would you mind if you can mention for how many identities the 50M images are?
