[Under development]- Implementation of various methods for dimensionality reduction and spectral clustering implemented with Pytorch
[Under development]- Implementation of various methods for dimensionality reduction and spectral clustering with PyTorch and Matlab equivalent code.
Sample Images from PyTorch code
Drawing the second eigenvector on data (diffusion map)
Drawing the point-wise diffusion distances
Use with Pytorch for general purpose computations by implementing some very elegant methods for dimensionality reduction and graph spectral clustering.
In this repo, I am using PyTorch in order to implement various methods for dimensionality reduction and spectral clustering.
At the moment, I have added Diffusion Maps  and I am working on the methods presented in the following list (as well as some other that I will add in the future).
Except from some examples based on 2-D Gaussian distributed clusters I will also add examples with face, food, imagenet categories etc.
In order to run these examples you need to have Pytorch installed in your system. I worked with Anaconda2 and Pytorch:
pytorch 0.2.0 py27hc03bea1_4cu80 [cuda80] soumith
(you can verify your pytorch installation by running
conda list | grep pytorch
Feel free to contact me for suggestions, comments etc.