/VCCA_pytorch

VCCA Pytorch Implementation on MNIST dataset

Primary LanguagePython

VCCA: Variational Canonical Correlation Analysis

This is an Pytorch implementation of Deep Variational Canonical Correlation Analysis (VCCA) in Python.

Variational CCA and Variational CCA Private [VCCA, VCCAP]

VCCA-private:

Deep Variational Canonical Correlation Analysis

Training

5 epochs:

view1 view2

50 epochs:

view1 view2

Generation

Dataset

The model is evaluated on a noisy version of MNIST dataset. Vahid Noroozi built the dataset exactly like the way it is introduced in the paper. The train/validation/test split is the original split of MNIST.

The dataset was large and could not get uploaded on GitHub. So it is uploaded on another server. You can download the data from:

view1

view2

save it in the same directory with python code.

Differences with the original paper

The following are the differences between my implementation and the original paper (they are small):

  • I used simple bianry cross entropy loss for two decoder networks.

Other Implementations

The following are the other implementations of VCCA in Tensorflow,