-
Hi there,
In this repository, ArcFace and others have some issues such as passing label to model is needed when prediction.
So I implemented new one.
https://github.com/ozora-ogino/asoftmax-tf
…
-
Hi,
Can you please give a brief idea about how to configure angular softmax as a loss function in the script?
Training steps I am not able to understand
-
-
I know it is not used in the default configuration. But what is it? Please give a reference. Thanks.
-
Why you use PLDA for AMSoftmax/ArcSoftmax/ASoftmax, did you try using simple cosine similarity?
-
when i use arcface loss in mnist, my error loss nan ? do you test your code accuracy ?
-
What did you mean by sphereface? is it Asoftmax or L-Margin or Isoftmax ? because I think it's not same as Asoftmax ...
If yes did you test it and get similar behavior to the original one
ghost updated
6 years ago
-
there are few questions I want to know:
1.
As I know there are 10 error pairs in all the 6000 pairs,so the upper limit should be 1-(10/6000)%=99.83%,and the accuracy in your paper is 99.86%
2.
Can…
-
-
I set the parameters as :
beta:1000
margin:4
scale=0.9997
beta_min=5
And after some iteration, the cross entropy loss suddenly become nan. Using the C++ layer and compile with mxnet. Does anyon…