Skip to content
Learning deep representations by mutual information estimation and maximization
Python
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
images Did clustering. Oct 27, 2018
README.md Add batch size to command line Jan 11, 2019
classification.py
cluster.py
models.py Now it actually trains the loss function! Nov 6, 2018
requirements.txt Add batch size to command line Jan 11, 2019
train.py

README.md

Deep InfoMax Pytorch

Pytorch implementation of Deep InfoMax https://arxiv.org/abs/1808.06670

Encoding data by maximimizing mutual information between the latent space and in this case, CIFAR 10 images.

Ported most of the code from rcallands chainer implementation. Thanks buddy! https://github.com/rcalland/deep-INFOMAX

Pytorch implementation by the research team here

Current Results (work in progress)

airplane automobile bird cat deer dog frog horse ship truck
Fully supervised 0.7780 0.8907 0.6233 0.5606 0.6891 0.6420 0.7967 0.8206 0.8619 0.8291
DeepInfoMax-Local 0.6120 0.6969 0.4020 0.4226 0.4917 0.5806 0.6871 0.5806 0.6855 0.5647

alt_text

Figure 1
Top: a red lamborghini, Middle: 10 closest images in the latent space (L2 distance), Bottom: 10 farthest images in the latent space.

Some more results..

alt_text

alt_text

alt_text

alt_text

You can’t perform that action at this time.