WeidiXie / VGG-Speaker-Recognition

Utterance-level Aggregation For Speaker Recognition In The Wild
362 stars 98 forks source link

questions about downloading pre-trained model #49

Closed lyu-joe closed 4 years ago

lyu-joe commented 4 years ago
Hi, i have download  your pre-trained weights to a model , then i trained the model using Voxceleb2, but its loss is 9 ,acc is 0.001 ,It’s as if it’s the same as no download.  it shoud be low loss and acc is about 0.92.do you know why 
Looking forward to your reply
WeidiXie commented 4 years ago

Because you are re-initializing the last layer classifier. Try initializing the entire model (feature + classifier), and load all weights (81 layers).