search

basveeling / wavenet

Keras WaveNet implementation
https://soundcloud.com/basveeling/wavenet-sample
1.06k stars 219 forks source link

Should an increase in dilation rate reduce the number of training parameters? #39

Closed maksimbaz closed 5 years ago

maksimbaz commented 5 years ago

Because I use keras model.summary and I noticed, that number of parameters stays the same if I change dilation_rate.

basveeling commented 5 years ago

Good questions! Dilation just spreads out the kernel with gaps in between, so the number of parameters should stay the same.