songweiping / tcn-tf Goto Github PK
View Code? Open in Web Editor NEWTensorFlow Implementation of TCN (Temporal Convolutional Networks)
TensorFlow Implementation of TCN (Temporal Convolutional Networks)
Do you use the weight normalization in your code?
File "wnconv1d.py", line 27, in
class _WNConv(convolutional_layers._Conv):
cant find _Conv in convolutional_layers
I think you may be performing weight normalization incorrectly for 1D convolutions.
In wnconv1d.py on line 58 you perform the following:
self.kernel = tf.reshape(g,[1,1,num_filters]) * nn_impl.l2_normalize(kernel, [0, 1, 2])
This l2 normalization normalizes over axes [0, 1, 2]. I believe this is incorrect for 1D convolutional weight normalization as you are performing l2 normalization over the filter dimension.
These axes would be correct if you were performing 2D convolution, since you would be performing l2 normalization over the two spacial and one input channel dimensions, but since you have only a single spacial dimension in 1D convolutions I think you may want to change your normalization axes to [0, 1].
If you want to maintain a rank-independent _WNConv layer you may want to generate those axes based on the provided rank or shape of kernel. Please let me know if I missed something here.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.