Coding Image Segmentation with UNet from first principles | Football Computer Vision

Показать описание

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:

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:

ConvNets Visualized and Explained:

Meta's Segment Anything Model Paper explained:

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

Рекомендации по теме

Комментарии

you just earned a new subscriber
love your content

himaliamit

Curious why you chose 2-strided conv on the downscaling "for expressiveness", but then upsample nearest on the way back up.

Great vids! I prefer more deep intuition-based discussion regarding the underlying maths, but that would take a lot more effort on your part.

HelloWorlds__JTS

can we get the access to the code for this project its really interested as i am a big football fan

gajendrasinghdhaked

I’m curious to know the rationale behind combining loss functions. Do you initially know that X loss function will do x task, and Y loss function will do y task. And then you combine both losses?
Or is there some deep literature done to decide which losses do what, and hope they work as expected?

thierrym

Hello, could you please upload tutorials to provide direction on referring image segmentation (RIS) research?

bushrarafiachowdhury

What are its advantages and disadvantages over YOLO?

revimfadli

Coding Image Segmentation with UNet from first principles | Football Computer Vision

Coding Image Segmentation with UNet from first principles | Football Computer Vision

Implement and Train U-NET From Scratch for Image Segmentation - PyTorch

The U-Net (actually) explained in 10 minutes

1. Transform Your Image Segmentation with U-NET

PyTorch Image Segmentation Tutorial with U-NET: everything from scratch baby

What is U-NET?

Image Segmentation Tutorial | UNet | Oxford Pet Data | Keras Tensorflow

215 - 3D U-Net for semantic segmentation

Image segmentation with a U-Net-like architecture - Keras Code Examples

UNet for Image Segmentation - What You Need To Know! - Computer Vision

Image Segmentation with U-Net in Python | @codewithsanthosh

3D Image Segmentation CT MRI with a 2D UNET Part1 Data preparation

Unet++ Model for Image Quality Detection: Model and Python Code Explained

73 - Image Segmentation using U-Net - Part1 (What is U-net?)

3D Image Segmentation (CT/MRI) with a 2D UNET - Part1: Data preparation

Training U-NET in Google Colab: A Step-by-Step Guide

Road Lane Detection with VGG-UNet on TuSimple Dataset | Image Segmentation Tutorial

228 - Semantic segmentation of aerial (satellite) imagery using U-net

Image Segmentation With Unet Pytorch

MRI Brain Tumor Segmentation Using ResUNet Deep Learning Architecture

219 - Understanding U-Net architecture and building it from scratch

Unet for Multi-class Segmentation

78 - Image Segmentation using U-Net - Part 6 (Running the code and understanding results)

Training U-NET on Original Dataset: A Step-by-Step Tutorial