Introduction
The aim of this article is to write down and describe my effort to dive into pruning methods for neural networks. It reflects the knowledge I gained and which I share for a discussion. It is not a tutorial or a teaching material: I am in the process of discovering this field myself.
Key takeaways
What I discovered is that on one hand there is an active research in the field. On the other hand, doing pruning in practice is not a well-established field. There are methods that implement pruning in PyTorch, but they do not lead to faster inference time or memory savings. The reason for that is that sparse operations are not currently supported in PyTorch (version 1.7), and so just assigning weights, neurons or channels to zero does not lead to real neural network compression. …
Introduction
In this article I describe how one can set up a continuous integration / continuous delivery (CI/CD) pipeline using GitHub.
This text is inspired by two sources. First one is “Nine simple steps for better-looking python code” by Vladimir Iglovikov. He gives the keys to better coding practices with CI/CD systems as its core. It is a great article and I wrote mine following the steps outlined there. So, “A practical guide for better-looking python code” is an accompanying/practical guide to Vladimir’s text. …
About
