[NEW COURSE] Machine Learning: Modern Computer Vision & Generative AI

Hello friends!

Click here if you don’t want to read my little spiel: https://deeplearningcourses.com/c/computer-vision-kerascv

Decided to take a little break from making math courses and do something very practical.

This course contains essentially no theory (unless it’s optional or absolutely critical to attain competence with the code), and it covers 3 main applications of computer vision:

1) Image recognition / classification: both pretrained models and fine-tuning

2) Object detection: both pretrained models and fine-tuning

3) Stable Diffusion and Generative AI

This course covers the “missing piece” from my original Computer Vision course, which was fine-tuning / training an object detection model from scratch. The libraries to do so simply weren’t good or didn’t exist. Briefly, I added an update to the course that showed how to do this, but the library we used quickly became obsolete and the dataset we used was even taken down.

Because this course uses KerasCV, which is an official Keras library backed by Google, my hope is that it will have much greater longevity. Additionally, we will also look at how you can create your own custom object detection datasets using a GUI to annotate your images.

Sound like fun? It is!

Note: Stable Diffusion section is still in the works and will be added in the coming weeks.