#Parameter is zero for gru and attention layer?

shenweichen / DSIN

Code for the IJCAI'19 paper "Deep Session Interest Network for Click-Through Rate Prediction"

https://arxiv.org/abs/1905.06482

Apache License 2.0

433 stars 132 forks source link

#Parameter is zero for gru and attention layer? #13

Closed arsenezhang closed 2 years ago

arsenezhang commented 4 years ago

Hello, I am running you baseline train_dien.py add ` names = [weight.name for layer in model.layers for weight in layer.weights] weights = model.get_weights()

for name, weight in zip(names, weights):
    print(name, weight.shape)`

to print variable in model and get

why there is no parameter for gru and attention layer? I user model.summary() also show no parameter for these two layer.

shenweichen commented 4 years ago

hi, some parameters are not included,this is due to the keras summary calculation logic.

arsenezhang commented 4 years ago

hi, some parameters are not included,this is due to the keras summary calculation logic.

thanks for reply. so the parameters in gru and attention layer is trained or not ?

shenweichen commented 4 years ago

They are all trained

arsenezhang commented 4 years ago

They are all trained

OK, thanks~