Backend - Keras
Here I talk about the last important thing in Keras - the backend. If you ever wanted to do something fancy with your Tensors or if you wanted to get intermediate layer outputs and representations or if you wanted to switch the backend from Theano to TensorFlow, then this is going to be really important for you.
I start off with introducing the config file that Keras has and then go through the contents of the file (and what you can do with them.)
After this, I explain how to import the backend, make a placeholder (aka an input), make variables, make uniform variables, concatenate, and a bunch of other stuff that’s in the backend. This is useful if you want to translate TensorFlow applications to Theano applications.
I then walk you through a few more useful backend methods and show you how and when to use them. Finally, I show you a cool application of these backend methods (where I show off what an intermediate layer in Keras would be in two separate ways).
Links:
1) Link to my Scikit Learn tutorial - A Bit of DataScience and Scikit Learn: • Intro to Scikit Learn
2) The Hitchhiker's Guide to Python - one of the best handbooks to the installation, configuration, and usage of Python that I have come across: http://docs.python-guide.org/en/latest/
3) Link to Keras: https://keras.io
4) Link to TensorFlow: https://www.tensorflow.org
5) GitHub link to a-bit-of-deep-learning-and-keras notebooks: https://github.com/knathanieltucker/a...
6) Link to the History of Deep Learning video will be up soon!
Watch video Backend - Keras online without registration, duration hours minute second in high quality. This video was added by user Data Talks 29 October 2017, don't forget to share it with your friends and acquaintances, it has been viewed on our site 6,134 once and liked it 62 people.