-
Notifications
You must be signed in to change notification settings - Fork 130
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
how to set the m when the feature without norm? #6
Comments
When we don't use the feature normalization, it is still necessary to use annealing strategy to set the m like the lambda in SphereFace. So I need to change the code to add the annealing strategy. I will give an example tomorrow. |
The example is uploaded. You also need to update the label_specific_add_layer to get the annealing codes. Note that I am still running the experiment to reproduce the result, so the prototxt may be changed in the next a few hours... By the way, I can get similar results on LFW BLUFR with normalization by finetuning the network using scale 60 and margin 0.4 after iteration 16000. Maybe you can also try this way. |
Thanks a lot! I will have a try. |
Hi, your paper shows the result of AM-Softmax w/o FN with the m = 0.35 and 0.4.
(1).with FN : Fai = s * (cos(theta) - m) s=30, m=0.35
#prototxt
layer {
name: "fc6_l2"
type: "InnerProduct"
bottom: "norm1"
top: "fc6"
param {
lr_mult: 1
}
inner_product_param{
num_output: 10516
normalize: true
weight_filler {
type: "xavier"
}
bias_term: false
}
}
layer {
name: "label_specific_margin"
type: "LabelSpecificAdd"
bottom: "fc6"
bottom: "label"
top: "fc6_margin"
label_specific_add_param {
bias: -0.35
}
}
layer {
name: "fc6_margin_scale"
type: "Scale"
bottom: "fc6_margin"
top: "fc6_margin_scale"
param {
lr_mult: 0
decay_mult: 0
}
scale_param {
filler{
type: "constant"
value: 30
}
}
}
layer {
name: "softmax_loss"
type: "SoftmaxWithLoss"
bottom: "fc6_margin_scale"
bottom: "label"
top: "softmax_loss"
loss_weight: 1
}
(2).w/o FN : s not needed, Fai = ||x|| * cos(theta) - m, still use m = 0.35?
#prototxt
layer {
name: "fc6_l2"
type: "InnerProduct"
bottom: "norm1"
top: "fc6"
param {
lr_mult: 1
}
inner_product_param{
num_output: 10516
normalize: false
weight_filler {
type: "xavier"
}
bias_term: false
}
}
layer {
name: "label_specific_margin"
type: "LabelSpecificAdd"
bottom: "fc6"
bottom: "label"
top: "fc6_margin"
label_specific_add_param {
bias: -0.35
}
}
layer {
name: "softmax_loss"
type: "SoftmaxWithLoss"
bottom: "fc6_margin"
bottom: "label"
top: "softmax_loss"
loss_weight: 1
}
Can you show your prototxt and trainning log? thx.
The text was updated successfully, but these errors were encountered: