Segment Anything - Model explanation with code

[@umarjamilai]

As always the slides are freely available: github.com/hkproj/segment-anything-slides

[@wingw4556]

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

[@pieter-cs]

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

[@umarjamilai]

Thank you for your kind words, @pierret00 Please stay tuned, more videos coming soon

[@ArunReddyAnugu]

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

[@DiegoSilva-dv9uf]

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

[@harpbeat500]

I was actually expecting me to watch this, but it was very informative

[@0jaxay0]

Very helpful, thanks! Please keep uploading 🙂

[@expectopatronum2784]

23:39 -> loved that intuitive explanation!

[@deeplearningexplained]

Hey Umar, Great work on this video! Keep it up!

[@sarahgarcia3063]

Really great explanation !! Thanks !

[@akhil1273]

Amazing Content. Clearly Explained !!!

[@madhurjindal1364]

Great explanation man!

[@oiooio7879]

Thank you! This is really helpful

[@andywang945]

The video is awesome.

[@zhuosu624]

Amazing explanation!

[@rohollahhosseyni8564]

Great job

[@syedabdul8509]

A video for coding SAM from scratch would be entertaining!

[@hubertkanyamahanga2782]

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!

[@carlosjaviergarcialopezdeh9213]

awesome video man!

[@yuhaoli371]

Please do an explanation for SAM2!

[@Maximos80]

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

[@Alice-yq6yy]

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

[@alivecoding4995]

very nice!

[@Esra208]

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?

[@郭少-s6v]

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.

[@MostafaGholami-g9g]

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

[@scz668]

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

[@missmiir]

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

[@DiegoSilva-dv9uf]

Valeu!

[@kai-yihsu3556]

Thank you!!! This is very helpful