Gumbel-Softmax Variational Autoencoder with Keras
License: MIT License
Gumbel-Softmax Variational Autoencoder with Keras.
This Keras based implementation of Categorical Reparameterization with Gumbel-Softmax. The code is based on Eric Jang's tutorial
You can run the Binder to get results like the following input-latent code-output triplet:
Also, you can visualize the latent code in 2D using Hamming distance based t-SNE:
I think this is a nice way to look into image hashing for image retrieval/search/etc. I'm excited to check how it scales up to real images...
Hi， thanks for the good work. However I am confused how you sample the Gumbel noise.
In the sampling function, you just sample the 'Gumbel noise' from a 'uniform' distribution:
U = K.random_uniform(K.shape(logits_y), 0, 1)
y = logits_y - K.log(-K.log(U + 1e-20) + 1e-20) # logits + gumbel noise
I wander if it is right??? Looking forward for the answer~ Thanks
Hi Eder,
Thanks for the Keras implementation! I'm excited about this idea as well. (Hopefully) quick question: I'm interested in learning an autoencoder for the output features of some other CNN (VGG16), so I'd like to maximize the cosine similarity of x and x_hat. Presumably this means I have to change
return data_dim * binary_crossentropy(x, x_hat) - KL
to something else, since it doesn't seem like binary_crossentropy makes sense in this context. Any thoughts on what it should be changed to? (I'm new to variational methods, so I'm trying to derive the answer myself right now, but thought I'd post the question here as well..)
Thanks!
Ben
I can't find this module in here:
https://github.com/AgnezIO/agnez.git@55657e5148ce58493f1847a
would u uploAD it again pls?
Thanks for uploading this. However, there is an error.
In the loss computation, you have elbo = data_dim * bce(x, x_hat) - KL.
It should be elbo = data_dim * bce(x, x_hat) + KL instead.
React
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
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
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.
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.