Segment Anything - Model explanation with code

preview_player
Показать описание
Full explanation of the Segment Anything Model from Meta, along with its code.

Chapters
00:00 - Introduction
01:20 - Image Segmentation
03:28 - Segment Anything
06:58 - Task
08:20 - Model (Overview)
09:51 - Image Encoder
10:07 - Vision Transformer
12:30 - Masked Autoencoder Vision Transformer
15:32 - Prompt Encoder
21:15 - Positional Encodings
24:52 - Mask Decoder
35:43 - Intersection Over Union
37:08 - Loss Functions
39:10 - Data Engine and Dataset
41:35 - Non Maximal Suppression
Рекомендации по теме
Комментарии
Автор

I am a undergraduate student learning AI, your videos help me a lot. Thanks for the selfless work you are doing.

wingw
Автор

I am a undergraduate student learning ML, your videos help me a lot. Thanks for the selfless work you are doing.

ArunReddyAnugu
Автор

Please keep making this kind of videos Umar! You're really a gifted teacher.

pierret
Автор

It's amazing how you can make this difficult subject much easier and more fun to learn! Thank you!

DiegoSilva-dvuf
Автор

23:39 -> loved that intuitive explanation!

expectopatronum
Автор

Very helpful, thanks! Please keep uploading 🙂

jaxay
Автор

Amazing Content. Clearly Explained !!!

akhil
Автор

Hi Umar, thanks for this amazing code explanation. Just one question, how is the prediction_iou computed in the Automatic Mask generation of SAM? I am asking because we only have the model's prediction and to compute iou you need ground truth labels. Thanks!

hubertkanyamahanga
Автор

incredible explanation! would you be interested in reviewing the SEEM (Segment Everything Everywhere All at Once) model?

Maximos
Автор

How does SAM calculate the predicted IoU for our output masks, if it doesn't have a ground truth for the given image?

Alice-yqyy
Автор

thanks a lot. how can we access to codes that explained in video?

wklusmy
Автор

One question regarding the Vision Transfomrer, even if this is not the main topic:
Why do they use the FIRST Token? Wouldn't usually the LAST token caputre all the information of the before seen ones?

Esra
Автор

Is there any way we can mask same object with same colors ?

missmiir
Автор

A video for coding SAM from scratch would be entertaining!

syedabdul
Автор

Nice video!
I think your understanding of the source code is really good.
Could you please share your annotated code? It will be very helpful for my undergraduate graduation project.

urkfwfl
Автор

based on python roadmap, what topic should i focused to sir?

scz