Code Monkey home page Code Monkey logo

tcn-tf's People

Contributors

songweiping avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar

Forkers

levstyle templeblock stevenlol eerstar howieeeeeeee noke8868 tspannhw libin19861023 ziganlan tedrepo jzinsa chenghu17 liu-nlper gentle-superman ztianle weeido mooreandmoore yunyouhuang liyongze tianrongchen lalalli bobz653 windstudent sunhongpeng wingerd maybeimaginary wuyifanisai kristenxy crystal22 xiaoanshi tonylibing sycamoretree

tcn-tf's Issues

TCN

Do you use the weight normalization in your code？

1D Weight Normalization Issue

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.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.