Details about training dnn_age_predictor_v1.dat.bz2 about dlib-models

[davisking]

It's trained from scratch. No pretraining.

…

On Mon, Dec 12, 2022 at 2:04 AM perets-dev ***@***.***> wrote: Hi, team, may I ask, you said about dnn_age_predictor_v1.dat.bz2 model: "This model is thus an age predictor leveraging a ResNet-10 architecture", so you just use ResNet-10 architecture or use pretrained ResNet-10 model (transfer learning)? — Reply to this email directly, view it on GitHub <#47>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABPYFRZ2YSZBGJ2TXVRJIKLWM3E6LANCNFSM6AAAAAAS3SBKAE> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[perets-dev]

Thanks for fast reply)

[perets-dev]

Excuse me, davisking, I have edited this question a bit a while ago before you answered to this question (this: #47 (comment)), so, you saw (may be) a previous version of the message. Could you view this question again? Thanks) (on github)

[davisking]

I don't know anything more about it beyond what is said here https://github.com/davisking/dlib-models#dnn_age_predictor_v1datbz2

[perets-dev]

Thanks for the reply