MLT __init__ Session #4 - SSD: Single Shot MultiBox Detector

[@youssefelassfouri9659]

amasing video , clear and direct. please never stop making these !! thank you

[@go64bit]

Amazing lecture. Very good explanation of SSD and its EfficientDet descendants.

[@logansizemore4735]

Best description I found. Good presentation. I love the visuals.

[@MyungeinHan]

This is really ground breaking! I love your explanation. Straight to the point & Simple.

[@MLTOKYO]

We'll pass the feedback on! :)

[@gennarofarina94]

Many compliments. This is a great introduction to SSD and its directions for improvement.

[@danielkusuma6473]

Very clear explanation and description of basically the original paper. Thank you!

[@19916718514]

best explaination on ssd i have ever found!

[@hole386]

Finnaly someone explaining how they actually make detections. So many people on here gloss over that part, and explain nothing about how the featuremaps are turned into boxes.

[@AmlanPanigrahi]

This is so clean and thorough!

[@atticross]

You have fantastic pedagogical skills. Thanks for the clear and lovely explanations

[@hanshima_]

Thanks for your generosity to teach this topic.

[@RajkamalUdayasuriyan]

Thank you for this wonderful Video, May I know how the default bounding boxes are encoded and what are their default location , size and aspect ratio in a feature map ?

[@Paladin1983PL]

Where can I get coordinates of the default 8732 boxes? I need to interpret the raw output localization tensor (the one with size [1,4,8732]) using C++ (LibTorch) so I can't use nvidia_ssd_processing_utils for that. I understand how to calculate the final bounding boxes but I don't have the default box data (dx, dy, dw, dh).

[@kotanvich]

Thanks a lot, great and clear explanation

[@asifmehmood6803]

Could you please make videos on RCNN and its variants with focus on RPN?

[@lackofsleep7653]

You’re wonderful and save my life!!!!

[@hosseinmadadi9141]

it was very useful and thank you for your time!

[@mariamIbrahim5848]

very clear and helpful thank you

[@from-chimp-to-champ1]

Beautiful lecture, thank you sir! May I just ask a little question? On the GIF visualizations that you show, it intuitively seems like we perform convolution of default bounding boxes with the feature maps of different scales. But it is written, that the actual size of convolutional blocks is 3 x 3. Could you clarify, how convolutions of feature maps with 3 x 3 blocks "intuite", with which default bounding box the network is working? Thank you very much! Sincerely, Pavel

[@granatapfel6661]

Can I use your presentation for my university project?

[@yasminemohamed5157]

such a great video, thank you!

[@clashtm8210]

Great lecture.

[@antonioconsiglio95]

Thanks for sharing, good explanation.

[@harshdevmurari007]

crystal clear explaination

[@lotfilofti6220]

in 6:27 you have 6 results concatenated in the detection block (detection 8732 by class), but in 11:55 you have only 5 outputs (features maps) ??????????????????????????????????????????????????????????????????????????????????????????????!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

[@AIandtheworld]

This was amazing!

[@budiandraym8451]

is ssd using FFNN or CNN ?

[@rezarawassizadeh4601]

Very good explanation, but it seems your layers are not correct they are 6 layers not 5.

[@Ohjjin]

I like the jib of this guy’s jab

[@wurstachim]

svm = __support__ vector machine.

[@les3464]

I kept thinking that myself lol