How to Segment Footballers from live footage - The UNET and Image Segmentation Guide!

This video is about the amazing UNet architecture and how it can be used to train any Image Segmentation model. I go over the major reasons why convolutional neural nets, especially the UNet are so good at image-segmentation tasks, going in deep with how to arrange a dataset, augment data, and code up a Image Segmentation system like this on your own using Pytorch. For accessing the code, animations, narration scripts, slides, etc for the video, consider joining the channel as a Youtube member or a Patron in Patreon. Read about perks here: https://www.patreon.com/NeuralBreakdownwithAVB https://www.youtube.com/@avb_fj/join I specifically looked at a Footballer segmentation dataset, which I must say was pretty fun for me to try. Here is the Kaggle link if you guys want to play with it: https://www.kaggle.com/datasets/ihelon/football-player-segmentation ConvNets Visualized and Explained: https://youtu.be/JV_d_OKhhL8 Meta's Segment Anything Model Paper explained: https://youtu.be/OhxJkqD1vuE Timestamps: 0:00 - Intro 0:39 - Overview 2:20 - Dice & Focal Loss 3:44 - Segmenting Videos 4:19 - UNet Deep Dive 7:44 - The Point of UNet 8:35 - Autoencoders vs UNet 9:58 - Fun next steps #ai #deeplearning #machinelearning