A two-stream convolutional neural network for learning abitrary similarity functions over two sets of training data
The code in this repo belongs to the following blog post http://www.priorlabs.com/2017/04/06/two-stream-convolutional-network-for-predicting-social-matches-in-linkedin-data/
The code has has been tested with TensorFlow v 0.10 and Python 2.7, but should be safe with Python 3 too.
To run the MNIST-example:
python train.py