This post contains details of how I set up my shell and environment. I use Windows, Mac, and Linux on a daily basis, so I have different setups for different purposes, but I try to make them similar when I can. You can see the softwhere I use and how I customize it in the linked posts; this post will focus on setup.

This post contains details of how I set up my shell and environment. I use Windows, Mac, and Linux on a daily basis, so I have different setups for different purposes, but I try to make them similar when I can. You can see the softwhere I use and how I customize it in the linked posts; this post will focus on setup.

I ran into an interesting issue when debugging in Python that I thought was worth sharing. It came up when I was visualizing some results from an object detector. I had a class for an object detector and one of the things it would check was that each prediction was associated with a valid object in the object dictionary. Here is a mock-up of the relevant parts (this is not the real class, just a toy example so as not to distract from the point).

This posts contains some of my notes from switching to PyTorch after having worked with TensorFlow and Keras for a long time.

There are a lot of great resources on the web that contain implementations of deep learning architectures, but they can be a little hard to find. This post aims to highlight and categorize some of the best resources that I have found. Most repositories have either Tensorflow or PyTorch implementations, so this post is divided by frameworks.

Convolutional neural networks (CNNs) are the powerhouse behind modern computer vision. And although they’ve grown in popularity with the rise of deep learning, they long predate it. In fact, CNNs have long been used with hand-crafted filters. These filters are used to extract specific components of an image which can then be used to understand what is in the image. This post demonstrates some of the most popular filters used in traditional computer vision. You’ll notice that in deep learning the word “filter” is sometimes used interchangeably with the word “kernel”. We’ll use both terms here as well.

This post provides a summary of some of the most important overhead imagery datasets for object detection. The aim of this post is to be a living document where I continue to add new datasets as they are released.