Question about downloading the model

[wanggongziZeo]

I can't download the model you provided,
and when I try to train my own caffemodel, the net accuracy only get 0.07, So what should I do to solve the problem?

[Iacopo Masi]

Hi @wanggongziZeo,
for the model I think you mean the face recognition network, right?
Why you can't download the network? What is the problem?

For your problem, I think you should debug your training.

Best,

[wanggongziZeo]

I can't open the ulr "https://goo.gl/3vygej", and there's no response for downloading the deep network "ResFace-101 a ResNet-101 network for face recognition"(Can't access this site)
Another question，I try VGG16 to train my own augmentation images(25 person, training images 34,836, test and validation are all 11612), but I only get about 0.86 accuracy, So how could I do to improve my acc, Thanks.

[Iacopo Masi]

Can you share with me your email address? I will point to the model to download.

…

On Tue, May 8, 2018 at 4:22 AM, wanggongziZeo ***@***.***> wrote: I can't open the ulr "https://goo.gl/3vygej", and there's no response for downloading the deep network "ResFace-101 a ResNet-101 network for face recognition"(Can't access this site) Another question，I try VGG16 to train my own augmentation images(25 person, training images 34,836, test and validation are all 11612), but I only get about 0.86 accuracy, So how could I do to improve my acc, Thanks. — You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub <#21 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AD_NH2Ga4DCDTSv5fXp-vIQinnDNImZnks5twYACgaJpZM4T0fEQ> .

[wanggongziZeo]

Yeah, [e-mail], Thanks
And, could you please send me your train.prototxt or deploy.prototxt file?