Giter Club home page Giter Club logo

capsnet-tf's Introduction

Hello 😄

I am Doyup Lee. Now, I am an AI researcher at Runway, New York.
I definetly believe that machine learning can make human life much happier.
Of course, I love to learn new technologies.

Research Interests

  • Large-Scale Generative Models
  • Multi-modal and unified representation learning
  • Training DNNs with limited labels
  • Robustness of deep learning and Anomaly Detection
  • Technology Innovation

Contact

capsnet-tf's People

Contributors

leedoyup avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar

Forkers

jihoonl donimst rosssong

capsnet-tf's Issues

Reconstruction Mask for Multi-MNIST dataset

Can you please explain the code referenced below for multi MNIST dataset? Especially the part where you create recon_mask_0 and recon_mask_1, and then later add them.
Any help would be highly appreciated. Thank You.

CapsNet-tf/model.py

Lines 115 to 134 in 0727864

else:
if self.sess.run(self.recon_with_label) == True:
mask_target = tf.nn.top_k(self.input_y, 2).indices
else:
mask_target = self.multi_pred_label
recon_mask_0 = tf.one_hot(mask_target[0], depth=self.n_digit, name='mask_output_0')
recon_mask_0 = tf.multiply(self.digit_caps, recon_mask_0, name='mask_result_0')
recon_mask_0 = tf.layers.flatten(recon_mask_0, name='mask_input_0')
recon_mask_1 = tf.one_hot(mask_target[1], depth=self.n_digit, name='mask_output_1')
recon_mask_1 = tf.multiply(self.digit_caps, recon_mask_1, name='mask_result_1')
recon_mask_1 = tf.layers.flatten(recon_mask_1, name='mask_input_1')
recon_mask = recon_mask_0 + recon_mask_1
with tf.variable_scope(name) as scope:
hidden1 = fc_layer(recon_mask, self.recon_h1, activation='relu',name='hidden1')
hidden2 = fc_layer(hidden1, self.recon_h2, activation='relu',name='hidden2')
output = fc_layer(hidden2, self.recon_output, activation='sigmoid',name='reconstruction')

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.