Cutting Edge Deep Learning for Coders

Other,, Summer 2018 , Prof. Jeremy Howard

Updated On 02 Feb, 19


Welcome to thenew 2018 editionof fast.ai's second 7 week course,Cutting Edge Deep Learning For Coders, Part 2, where you'll learn the latest developments in deep learning, how to read and implement new academic papers, and how to solve challenging end-to-end problems such as natural language translation. You'll develop a deep understanding of neural network foundations, the most important recent advances in the fields, and how to implement them in theworld's fastest deep learning libraries, fastai and pytorch.


Lecture 2: Lesson 9: Deep Learning Part 2 2018 - Multi-object detection

4.1 ( 11 )

Lecture Details

NB: Please go to http://course.fast.ai/part2.html to view this video since there is important updated information there. If you have questions, use the forums at http://forums.fast.ai.

In today’s lesson we’ll move from single object to multi-object detection. It turns out that this slight difference makes things much more challenging. In fact, most students found this the most challenging lesson in the whole course. Not because any one piece is highly complex, but because there’s a lot of pieces, so it really tests your understanding of the foundations we’ve learnt so far. So don’t worry if a lot of details are unclear on first viewing – come back to this lesson from time to time as you complete the rest of the course, and you should find more and more of it making sense!

Today’s focus is on the single shot multibox detector (SSD). This is a way to handle multi-object detection by using a loss function that can combine losses from multiple objects, across both localization and classification. It also uses a custom architecture that takes advantage of the difference receptive fields of different layers of a CNN. And we’ll see how to handle data augmentation in situations like this one where the dependent variable requires augmentation too. Finally, we’ll discuss and simple but powerful trick called focal loss which is used to get state of the art results in this field.



0 Ratings
comment person image


Excellent course helped me understand topic that i couldn't while attendinfg my college.

comment person image


Great course. Thank you very much.