Tensorflow implementation of Adversarial Autoencoders

https://github.com/conan7882/adversarial-autoencoders-tf

by conan7882 • 8 years ago

64 10 8 years ago

github.com

jingleheimer• 8 years ago

This code is really good.

AstralStorm• 8 years ago

And impossible to use thanks to no license information.

edtruji• 8 years ago

MIT License, it was added after your post https://github.com/conan7882/adversarial-autoencoders-tf/blo...

Lorkki• 8 years ago

Though, in the finest academic tradition, once you try to actually run it, you'll find that it silently depends on a separate library written by the author, which you'll have to find yourself.

(In this case "tensorcv", which is in a separate repository: https://github.com/conan7882/DeepVision-tensorflow )

That aside, I agree that it's an easier read than most ML code.

conan7882• 8 years ago

I though I have removed all the dependency on 'tensorcv'. It turns out I forgot the dataflow part. Now it should be run without 'tensorcv'. Thanks for pointing out.

polynomial• 8 years ago

For this particular implementation, what are the advantages of using it for supervised or unsupervised learning? (in general?)

And if it's just being used for the MNIST dataset, is there a particular reason for using it in one or the other fashion?

locuscoeruleus• 8 years ago

From what I can gather the supervised approach allows you to only learn the representation for style rather than which digit it is. The only reason to use one over the other is to demonstrate that it works, I guess?

amelius2• 8 years ago

Question: what framework is used mostly by academic researchers these days for DL?

nabla9• 8 years ago

Tensorflow, although PyTorch is gaining popularity.

amelius2• 8 years ago

Ok. I guess in this case the authors used TF because three of the authors work at Google.

Tensorflow implementation of Adversarial Autoencoders

Related Stories