This repo contains materials for use in a TensorFlow workshop. The accompanying slides are here.
Contributions are not currently accepted. This is not an official Google product.
This document points to more information for each step in the workshop.
- Installation
- Building a small starter TensorFlow graph
- Introducing MNIST, and building a simple linear classifier in TensorFlow.
- Using TensorFlow's high-level APIs to build an MNIST DNN Classifier, and introducing TensorBoard.
- Building the same classifier using TensorFlow's "low-level" APIs.
- Building custom
Estimators for a version of MNIST that uses CNNs. - Running distributed MNIST using Cloud ML.
- Transfer learning: using a trained model to 'bootstrap' learning new classifications.
- Building a word2vec model using a Custom Estimator, and exploring the learned embeddings. Introducing TFRecords.