CurricularFace

CurricularFace copied to clipboard

final_target_logit = torch.where(target_logit > self.threshold, cos_theta_m, target_logit - self.mm)

1

In MV-softmax, the released code use easy_margin like following: ``` final_gt = torch.where(gt > 0, cos_theta_m, gt) ``` but the official arcface implement does not use easy_margin, like following: ```...

powermano

Model evaluation

1

Excuse me, I have a problem why the best threshold was used in evaluation rather than a fixed threshold？ Shouldn't we be using a fixed threshold in practical application?

FengMu1995

关于evaluate的问题

1

你好，想问一下为什么在evaluate文件中只用了backbone，没有用head

yizhicainiao2022

Error in evaluate.py

1

in File utility.py I meet the error get_val_pair(path, name): carray = bcolz.carray(rootdir = os.path.join(path, name), mode = 'r') FileNotFoundError: No such a file /public/share/dataset/Face/lfw/meta/sizes Can someone hep me with this?...

bigAndSmall

self.t = target_logit.mean() * 0.01 + (1 - 0.01) * self.t

1

Hello! In the paper, t should be calculated as:  It seems to be "self.t = target_logit.mean() * 0.99 + (1-0.99) * self.t" in the code. But found "self.t =...

CloudWalking0

Why in equation (8) derivitiveα are devided with sin(θj) ? where does this come from? I refer to this paper(CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition) Can anyone...

grmos

Bumps [numpy](https://github.com/numpy/numpy) from 1.14.2 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

can not perform same as your pretrained res101

13

hello Evaluation: LFW Acc: 0.9968333333333332, CFP_FP Acc: 0.8959999999999999, AgeDB Acc: 0.9726666666666667 it's my training result as 20 epoch , hyper param as you set .. acc on cfp-fp is quite...

ruiming46zrm

code: self.t = target_logit.mean() * 0.01 + (1 - 0.01) * self.t paper: t(k) = αr(k) + (1 − α)t(k−1) α = 0.99, r(k) = sum cosθyi arget_logit.mean() in your...

eeric

code: self.t = target_logit.mean() * 0.01 + (1 - 0.01) * self.t paper: t(k) = αr(k) + (1 − α)t(k−1) α = 0.99, r(k) = sum cosθyi arget_logit.mean() in your...

eeric