Once in a while, a Python package gets corrupted on your machine and you need to force pip to reinstall it. As of pip 10.0, you can run the following…
Sometimes you need to define your own Keras custom layer. This tutorial explains how custom layers work for tensorflow>=1.7.0 (up to at least 2.4.0) which includes a fairly stable version of the Keras API.
If you have a random sample drawn from a continuous uniform(a, b) distribution stored in an array x, the maximum likelihood estimate (MLE) of a is…
There are lots of ways to install TensorFlow, which means (unfortunately) there is no one-size-fits-all solution for uninstalling it.
The Pandas melt command unpivots tabular data, transforming it from wide to long format. To understand this operation, you have to know…
Object tracking is pretty easy conceptually. And if you have a good detector, simple methods can be pretty effective.
Cross entropy loss in PyTorch can be a little confusing. Here is a simple explanation of how it works for people who get stuck.
You can do vectorized pairwise distance calculations in NumPy (without using SciPy). This lets you extend pairwise computations to other kinds of functions.
DAGs are everywhere in scientific computing and understanding them is key to running large computations efficiently.
Informative names make programming easier. Here are a few suggestions you can use to write better names in your code.