CurricularFace

CurricularFace copied to clipboard

it was occur error to mask = cos_theta > cos_theta_m with multi gpu

1

dimension mismatch

eeric

t can not update correctly when use multiple gpu

2

It seems that when use multiple gpus for training, t start from 0 in every iteration. When use a single gpu for training, t is updated correctly.

MisayaZ

prepare training data

4

Could you tell me how to prepare the training data and the 'refined_ms1m.txt'? Thanks.

gaozhangyang

Performance and backbone network

4

Thanks for sharing a great work. In your code, you provided some backbone network ``` support: ['ResNet_50', 'ResNet_101', 'ResNet_152', 'IR_50', 'IR_101', 'IR_152', 'IR_SE_50', 'IR_SE_101', 'IR_SE_152'] ``` In the [Model Zoo...

John1231983

CurricularFace/head/metrics.py / target_logit = cos_theta[torch.arange(0, embbedings.size(0)), label].view(-1, 1)

wpd-mlb

calculate t was wrong

2

with torch.no_grad(): self.t = target_logit.mean() * 0.01 + (1 - 0.01) * self.t but your paper is: t(k) = αr(k) + (1 - α)t(k-1); where t0 = 0, α is...

Aruen24

what would be the output size of curricularface? would it return a scalar value or a tensor of dimension [batch_size,no_of_classes]?

mosszhd

I wonder, how to prepare the images in order to use the pre-trained model. 1. I guess that the images should be aligned and resized to 112x112, right? Your code...

JoMe2704

Hello teams, Can the Curricular Face or ArcFace be used for face recognition in a single image?

Darshan2701

Hello, author. First of all, thank you for sharing the project. I see that there are reviews in this project, but there is no prediction. I have a problem when...

lijain