These notes and tutorials are meant to complement the material of Stanford’s class CS230 (Deep Learning) taught by Prof. Andrew Ng and Prof. Kian Katanforoosh. For questions / typos / bugs, use Piazza. These posts and this github repository give an optional structure for your final projects. Feel free to reuse this code for your final project, although you are expected to accomplish a lot more. You can also submit a pull request directly to our github.
Hands-on sessions
Final Project
Introduction
-
Introducing the Project Code ExamplesIntroduction and installation
-
AWS setupHow to set up AWS for deep learning projects
Best practices
-
Splitting into train, dev and test setsBest practices to split your dataset into train, dev and test sets
-
Logging and HyperparametersBest practices to log, load hyperparameters and do random search
TensorFlow
-
Introduction to TensorflowGraph, Session, Nodes and variable scope
-
Building a data pipelineUsing Tensorflow tf.data for text and images
-
Create and train a ModelUsing tf.layers, tf.train, tf.metrics, Tensorboard
PyTorch