In this tutorial, Lukas Biewald (a former Stanford Robotics Lab engineer) shows us how he builds two robots able to run deep learning to do object recognition.
Both robots use the open source software library TensorFlow. The library comes with a prebuilt model called “inception” that performs object recognition.
Deep learning and a large public training data set called ImageNet has made an impressive amount of progress toward object recognition. TensorFlow is a well-known framework that makes it very easy to implement deep learning algorithms on a variety of architectures. TensorFlow is especially good at taking advantage of GPUs, which in turn are also very good at running deep learning algorithms.