[Adapt] Bonus in Today's Seminar

[黄圣蕾]

Hi adapters:

Sorry for the delay, the email I sent before is denied because it's too
big, and I found this mistake just now :( Sorry again, hope it is not too
late.

Today we will discuss an exciting topic in Artificial Intelligence - Object
Detection. And we will go through several simple deep learning models (from
RCNN, 2013 to RFCN, 2016) to see how could computer capture where the
object is and what it is.



Today's seminar requires you to have some pre-knowlege about CNN
(convolutional neural network), if you haven't heard it before, click here
<http://www.36dsj.com/archives/24006>. No need to be a master, just to know
what it is and why we use it.

Maybe you want to play with those models ahead, so I put them here:

RCNN: (caffe + matlab) https://github.com/rbgirshick/rcnn
fast-RCNN: (caffe + matlab) https://github.com/rbgirshick/fast-rcnn
faster-RCNN: (caffe + python) https://github.com/rbgirshick/py-faster-rcnn
*I RECOMMEND THE FOLLOWING TWOS:*
RFCN: (caffe + python) https://github.com/Orpine/py-R-FCN
YOLO: https://pjreddie.com/darknet/yolo/

I think it deserves you to come :)  Have a nice day!

P.S. Maybe I will ask some tough question :)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20170301/2757aaa5/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ???? 2017-03-01 ??9.03.46.png
Type: image/png
Size: 865248 bytes
Desc: not available
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20170301/2757aaa5/attachment-0001.png>