Did you reproduce megaface ?

[twmht]

Hi

Did you reproduce megaface result on pytorch?

thank you

[TreB1eN]

no, you can have a try

[twmht]

@TreB1eN

I tried mobilenet, but can't reproduce the paper's result (92%)

My result is only 87%

[TreB1eN]

I don't have clue about training Megaface, normally there are a lot of noises in the training set, how about try use emore dataset pretrained model here to test in Megaface test set ? See what is the accuracy ?

[twmht]

@TreB1eN

I did not train on megaface, I trained on refine MS-1M and test on megaface. Did you try to do that?

[TreB1eN]

I haven't

[ruiming46zrm]

@twmht

can you tell us your acc on cfp-fp by res50, mine is 87.5%

[TreB1eN]

0.9504 CFP-FP(%) by IR-SE50, pretrained model are provided

[ruiming46zrm]

0.9504 CFP-FP(%) by IR-SE50, pretrained model are provided

training refined-ms1m ,I can get LFW 99.52% but can't get cfp-fp so well , maybe something wrong.

[twmht]

@TreB1eN

Did you trained on refined-ms1m on IR-SE50?

[twmht]

@ruiming46zrm

Did you use this code without modification? I haven't tested cfp-fp yet.

[TreB1eN]

@twmht yes

[ruiming46zrm]

@twmht yes, ok

[twmht]

@TreB1eN

I can help to test the provided model in megaface.

[ruiming46zrm]

@twmht will you share mega test code if it's convenient~ ?

[twmht]

@ruiming46zrm

most of testing code is from insightface. Did you tried to reproduce the result on insightface?

[ruiming46zrm]

@twmht thanks, I don't know much about the megaface, I'm gonna try.

[twmht]

@TreB1eN and @ruiming46zrm

I just tried @TreB1eN 's provided resnet50 pretrained weight, but only got 90% on megaface.

but from deepinsight (https://github.com/deepinsight/insightface), they provide resnet50 which can get 97.64% on megaface.

since this is a huge gap, there might be some issues with pytorch implementation.

[twmht]

@TreB1eN

in addition, mobilenet only got 74% on megaface.

[ruiming46zrm]

provided resnet50 get 91.6% on megaface, my training only 89.9%

[yangyuke001]

@twmht will you share mega test code if it's convenient~ ? mainly gen_megaface.py for pytorch version,thanks a lot

[ruiming46zrm]

@yangyuke001 I have one , what's your weichat?

[yangyuke001]

yangyuke001

At 2019-01-07 08:23:09, "ruiming46zrm" [email protected] wrote:

@yangyuke001 I have one , what's your weichat?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

[ruiming46zrm]

yangyuke001 At 2019-01-07 08:23:09, "ruiming46zrm" [email protected] wrote: @yangyuke001 I have one , what's your weichat? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

user name unexist , mine is : ruiming46zrm

[cvtower]

Hello @ruiming46zrm, @twmht

The mega test code has to load a trained model and do inference, i mean it can not be tested during training, right? Then i have a question, this repo saves model per few iters, however, the best accuracy on different dataset may not always the same saved model. Shall we just take the best accuracy on each dataset as the final performance?

[ghost]

Hi, Do we need to normalize the images of Facescrub and Megaface before feeding them to the model to get features? Thank you for reading.

[gaow0007]

@TreB1eN and @ruiming46zrm

I just tried @TreB1eN 's provided resnet50 pretrained weight, but only got 90% on megaface.

but from deepinsight (https://github.com/deepinsight/insightface), they provide resnet50 which can get 97.64% on megaface.

since this is a huge gap, there might be some issues with pytorch implementation.

Could you share the test configs of MegaFace? Such as select how many images as galleryset?

[HulkMaker]

@TreB1eN and @ruiming46zrm I just tried @TreB1eN 's provided resnet50 pretrained weight, but only got 90% on megaface. but from deepinsight (https://github.com/deepinsight/insightface), they provide resnet50 which can get 97.64% on megaface. since this is a huge gap, there might be some issues with pytorch implementation.

Could you share the test configs of MegaFace? Such as select how many images as galleryset?

Could you share Megaface dataset since its stopping supported in their website. And I would like to test on it too. Thanks!