This repository contains both code and explanations of Computer Vision topics and books I've studied. Everything I've found most useful is neatly compiled here.
Since I mainly work with PyTorch and Deep Learning, this is the main focus of the repository. If you're looking for either TensorFlow, OpenCV or more general ML content, there are likely better resources. Still, the books and Youtube channels listed here will surely help.
Be aware: This repository focuses on studying and understanding Computer Vision concepts and implementations. As such, other concepts which I consider essential for development end up falling a bit out of scope. For real-world applications you should absolutely cover aspects such as model deployment, experiment tracking, Docker, Kubernetes, and cloud platforms.
Short summaries and information about books I've read and how they connected with me. In short, if they're there, I recommend the read.
Codes I've implemented either by myself or through Youtube lessons. I've found that coding, even if just writing code along with Youtube lessons, helped me a lot to internalize concepts and get more confortable with Pytorch.
These are MOOCs and Youtube channels which I've watched and recommend. Some of them are more theory-heavy and offer little to no code on lessons (e.g. CS231n), while some others I've watched mainly for the coding lessons (e.g. Aladdin Persson). The best mixture of both is probably from Vizuara.
Still, there is something there for everyone and I highly recommend you check them out.