Lesson 9: Cutting Edge Deep Learning for Coders

Today we’ll learn about the extraordinarily powerful and widely useful technique of generative models. These are models that don’t just spit out a classification, but create a whole new image, sound, etc. They can be used, for example, with images, to: improve photos (colorization, noise removal, increase resolution, etc); create art; find and segment (localize) objects; and much more...

We’ll try using this approach for super resolution (i.e. increasing the resolution of an image), and then you’ll get to try building your own system for rapidly adding the style of any artist to your photos.

[ericpb]

Video timeline:

00:00:30 Contribute to, and use Lesson 8 Wiki

00:02:00 Experiments on Image/Neural Style Transfer

00:05:45 Advanced tips from Keras on Neural Style Transfer

00:10:15 More tips to read research papers &
"A Neural Algorithm of Artistic Style, Sep-2015"

00:23:00 From Style Transfer to Generative Models

00:32:50 "Perpetual Losses for Real-Time Style Transfer
& Super-Resolution, Mar-2016"

00:39:30 Implementation notebook w/ re-use of 'bcolz' arrays from Part 1.

00:43:00 Digress: how "practical" are the tools learnt in Part 2, vs. Part 1 ?

00:52:10 Two approaches to up-sampling: Deconvolution & Resizing

01:09:30 TQDM library: add a progress meter to your loops

01:17:30 Fast Style Transfer w/ "Supplementary Material, Mar-2016"

01:27:45 Ugly artifacts like "checkerboard": cause and fixes; Keras UpSampling2D

01:31:20 ImageNet Processing in parallel

01:33:15 DeVISE research paper

01:38:00 Digress: Tips on path setup for SSD vs. HD

01:42:00 `words, vectors = zip(*w2v_list)`

01:49:30 Resize images

01:52:10 Three ways to make an algorithm faster:
memory locality,
simd/vectorization,
parallel processing

[CesareMontresor]

For Pillow-simd for OSX users.
Pillow-simd requires zlib headers but zlib is already provided by Apple, in order install first perform:

$ brew install zlib
$ brew link zlib --force (force to use brew version)
$ CC="cc -mavx2" pip install -U --force-reinstall pillow-simd

[monthspregnant]

The excel demo on deconvolutions was beautiful!

[Wangleineo]

The audio tracks of the part2 video are really bad, is the original recording like this?

[MasayoMusic]

Are they any subtitles for this video? I"m having trouble understanding what Jeremy is saying. The audio quality isnt very good :(