Lately I've been doing some experiences with Theano and Deep Learning. One thing that I really thought could help is to understand the workflow of a Theano algorithm through visualization of tensors' connections. After developing the model, I printed the prediction algorithm for a deep learning Neural Net with 2 hidden layers, 2 inputs X1 and X2, and a continuous output Y. I used Graphviz and pydot to generate the graphic with this line of code:

theano.printing.pydotprint(prediction, outfile="/Volumes/16 DOS/Python/prediction.png", var_with_name_simple=True)

It looks like this:

Views: 5365

Tags: Graphviz, deep, hidden, layers, learning, networks, neural, pydot, rubens, tensors, More…theano, zimbres


You need to be a member of Data Science Central to add comments!

Join Data Science Central

Comment by Anthony Wiggins on October 18, 2016 at 2:53am
Actually it makes sense and shows all the connections, kinda important for neural nets as connectivity is part of the paradigm for their function
Comment by Rubens Zimbres on October 7, 2016 at 9:28am

Xi Chen, this is the original file, generated by Graphviz

Comment by Xi Chen on October 7, 2016 at 9:14am

Is there a better way to print out the figure? It's kind of confusing.

© 2021   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service