This week in the Deep Learning Reading Group we worked through some introductory exercises on Tensorflow, based upon the provided tutorials and edited by Zeb and I. It’s targeted at those with minimal Python experience, but who have programmed in Matlab.
It’s largely self-explanatory; a collection of code examples with some discursive text, and a few snippets requiring you to fill in a few blanks. We go through:
- Basic addition and multiplication
- Working with Tensorflow sessions and variables
- Running a gradient descent by hand
- Using TF’s optimisers to do the gradient descent for us
- Basic plotting
You can download the iPython notebook here.
You should then be able to get it started in your instantiation of Tensorflow (tips on installation here) either by popping it into the local folder which you’re syncing with Docker, or, more straightforwardly, by going to Upload on the right hand side of your Jupyter interface:
Have fun! Let me know if you have problems or spot any issues.
Pingback: Deep Learning Practical 2: Decoding MNIST | Archy de Berker