Here is a little script I worked on to help automate the build out of a lab environment. I built this primarily to support a nested ESX and vCenter auto-deploy…
This is Part 2 in my short series on Keras Callbacks. As I stated previously, a callback is an object that can perform actions at various stages of training and is specified…
About 8 months ago I began to develop an instructor led Ansible Workshop that could be led from my place of work. We have a mini-datacenter lab and I found…
Training neural networks is an iterative process that can be very timeconsuming. Rarely do you get the optimal model on your first training run. You try a set of hyperparameters then…
Machine learning and deep learning are not trivial subjects. The breadth of the material is pretty amazing. How in the world can we wrap our heads around this mass of…
In this two part series, I discuss what I consider to be two of the most important hyperparameters that are set when training convolutional neural networks (CNNs) for image classification or object detection. These are learning rate and batch size. …
