dribnet Profile picture
9 Aug, 36 tweets, 29 min read
the architect #clip #pixelart Image
boxers and bulbs #clip #pixelart boxers (dogs and underwear)bulbs (plants and lights)
church and crow #clip #pixelart
(church... with cemetery?) ImageImage
daughter and detective #clip #pixelart ImageImage
explosion and electric fan #clip #pixelart ImageImage
factory and farm #clip #pixelart ImageImage
fish and frogs #clip #pixelart ImageImage
goat and grapes #clip #pixelart ImageImage
heaven and herbs ImageImage
igloo and ivy #clip #pixelart ImageImage
jaywalker and jellyfish #clip #pixelart ImageImage
knife and kiss #clip #pixelart
(on maximizing "kiss": well played CLIP) ImageImage
log and london #clip #pixelart ImageImage
museum and moonlight #clip #pixelart ImageImage
newspaper and nurse #clip #pixelart ImageImage
ocean and octopus #clip #pixelart ImageImage
pharmacist and pencil #clip #pixelart ImageImage
queue and quicksand #clip #pixelart ImageImage
restaurant and rice #pixelart #clip ImageImage
surgeon and singer #pixelart #clip ImageImage
shower and shampoo #pixelart #clip ImageImage
sari and shirt #pixelart #clip ImageImage
swimming pool and supermarket #pixelart #clip ImageImage
swan and sparrow #pixelart #clip ImageImage
sun and sky #pixelart #clip ImageImage
tea and theater #pixelart #clip ImageImage
undertaker and urine #pixelart #clip ImageImage
veterinarian and vegan #pixelart #clip ImageImage
wedding and widow #pixelart #clip ImageImage
wave and wings #pixelart #clip ImageImage
x-ray and xenomorph #pixelart #clip ImageImage
yacht and yakuza #pixelart #clip ImageImage
zygote and zoo #pixelart #clip ImageImage
I'll dedicate this rambling thread of words to the linguist Ray Jackendoff who studies semantics + computational theory of mind. This paragraph from his monograph debating the merits of studying the details individual words vs patters across many words is one of my favourites. Image
Here's a link to my colab if you'd like to give it a go yourself. This codebase builds off of previous work from many people including @advadnoun @RiversHaveWings @NerdyRodent as well as ClipDraw from @kvfrans @crosslabstokyo @err_more and @okw.
colab.research.google.com/github/dribnet…
And my next step with these is finding ways of limiting the color palette. If you enjoy this work and would like to contribute (and are comfortable with pytorch) feel free to offer up coding suggestions in this github issues thread. github.com/dribnet/clipit…

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with dribnet

dribnet Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @dribnet

17 Aug
Greetings from Wellington, New Zealand #pixelart #clip Image
Hello from Beirut
Skyline by @gorillasu #pixelart #clip Image
@gorillasu Hello Wisconsin!
Milwaukee skyline by @Develotec Image
Read 7 tweets
2 Jan 19
At the recent #neurips4creativity panel someone asked what areas of machine learning were recommend for newcomers, and I suggested exploring atypical algos such as image segmentation and how they might be repurposed.

let me explain further with using some of my students' work.👇
Semantic Image Segmentation is arguably one of the more mundane success stories of modern computer vision. The task is to label each pixel with a label - @jeremyjordan provides a good overview if you are unfamiliar: jeremyjordan.me/semantic-segme…
This past year I introduced it to my @vicuniwgtn design 2nd year undergraduates as part of a digital photography assignment. It seemed completely natural to students that (of course!) images can be decomposed into not only Red, Green, and Blue but also imperfect semantic labels.
Read 8 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!

:(