Comments (1)
Increase in dilation rate will result in "no change in total number of parameters and basic structure" yet "increase in receptive field (you can think receptive field is somehow like input range)". For example, if dilation rate is 1 and I have 3 layers, my structure's receptive field is 5 nodes from the input layer. However, if you increase the dilation rate to 3 then my receptive field is 8 nodes from the input layer. Without changing the number of parameters, you can increase the input size. That is the advantage of the dilated convolutional layers.
from keras-wavenet.
Related Issues (8)
- this implementation seems not same as deepmind's description HOT 1
- Missing 'validate.wav' and 'train.wav' HOT 4
- AtrousConvolution2D assertion error setting atrious rate. HOT 3
- Atrous Rate illegal for TF Backend HOT 1
- Bug in frame_generator? HOT 1
- Maybe this is a bug... HOT 1
- Did you implement the causal convolution part mentioned in the WaveNet paper? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from keras-wavenet.