taylorlu / ghostvlad-speaker

An tensorflow implementation of ghostvlad for speaker recognition
14 stars 9 forks source link

cluster center stay the same during training #6

Open FabianGroeger96 opened 3 years ago

FabianGroeger96 commented 3 years ago

Hi there

During training using the GhostVLAD layer, I have experienced that the cluster centres do not change their value, which means that they always stay at the same place during training. Is this an expected behaviour, or is this a bug in my training process?

To give you some context, I used the GhostVLAD layer after a ResNet18 architecture for an audio task. I adapted your exact code to fit my structure. All the initialization, layers and so on are like in your code.

I would appreciate your help 😄.