Super-convergence in deep learning is a term coined by research Leslie N. Smith in describing a phenomenon where deep neural networks are trained an order of magnitude faster then when using traditional techniques. The technique has lead to some phenomenal results in the Dawnbench project, leading to the cheapest and
Choosing a good learning rate is the most important hyper-parameter choice when training a deep neural network (assuming a gradient based optimization algorithm is used).
Choosing a learning rate that's too small leads to extremely long training times. Whereas a learning rate that's too large might miss the optimum and
(Note: this post was updated on 2019-05-19 for clarity.)
In this post we will look at an end-to-end case study of how to creating and cleaning your own small image dataset from scratch and then train a ResNet convolutional neural network to classify the images using the FastAI library.
(Updated April 2019)
I list the steps I followed for personal reference, which includes solving some minor issues I encountered in
The first major version of the FastAI deep learning library, FastAI v1, was recently released. For those unfamiliar with the FastAI library, it's built on top of Pytorch and aims to provide a consistent API for the major deep learning application areas: vision, text and tabular data. The library also