Fun experiment running DeepLab in realtimehttps://t.co/xG1PHPW6tn https://t.co/aI9xKvFPgr
— hardmaru (@hardmaru) May 26, 2020
Fun experiment running DeepLab in realtimehttps://t.co/xG1PHPW6tn https://t.co/aI9xKvFPgr
— hardmaru (@hardmaru) May 26, 2020
A neat TF2/Keras implementation of text-to-speech with Transformer. https://t.co/SBn9EyPf7T
— François Chollet (@fchollet) May 20, 2020
New NVIDIA Merlin, end-to-end pipeline for deep learning based recommender systems includes SOTA pre-trained models like Wide and Deep, NCF, VAE, DeepFM. Learn more: https://t.co/H8qRcdfjka #GTC20
— NVIDIA AI Developer (@NVIDIAAIDev) May 14, 2020
This Word Does Not Existhttps://t.co/gcUqp2SM0k
— hardmaru (@hardmaru) May 14, 2020
Fun project where @turtlesoupy trained a GPT-2 language model over the Oxford English Dictionary.
Sampling from it, you get realistic sounding words with fake definitions and example usage, e.g. pic.twitter.com/G1u0qjGwat
Will your next ophthalmology paper make it into a top journal? Why not use a Keras model to find out?https://t.co/lh045AoXmu
— François Chollet (@fchollet) May 6, 2020
Would be interesting to do feature importance analysis here
PixelMe: Convert your photo into Pixel Arthttps://t.co/ZV5BmUjc3nhttps://t.co/mSipIrIUiW pic.twitter.com/tf0hzogkfi
— hardmaru (@hardmaru) May 5, 2020
Very happy to see such a cool application of VQ-VAEs by our friends @OpenAI! Congrats! https://t.co/v01UvhnPRL
— Oriol Vinyals (@OriolVinyalsML) April 30, 2020
Just pushed the code of a chrome extension that turns every Instagram posts into 3d images using #3DPhotoInpainting. No GPU needed thanks to @GoogleColab but a bit of patience to set it up ;-)
— Cyril Diagne (@cyrildiagne) April 19, 2020
Demo: @parrstudio's amazing work
Code: https://t.co/59yJUvRHxE#AIUX #Interaction #ML pic.twitter.com/86mMBWdm7V
Social distancing is needed to keep us safe. So @LandingAI created this AI tool to help our customers in essential industries maintain #SocialDistancing in the workplace. We hope many people can benefit from these ideas. https://t.co/RukER1pNRw pic.twitter.com/34hBqT8Eak
— Andrew Ng (@AndrewYNg) April 16, 2020
The seaborn clustermap is a really fun tool. Here, it automatically clustered Meetup groups based on the number of overlapping members. Data was pulled from the meetup API. Several extra tweaks done with matplotlib pic.twitter.com/rBsdzKZQSW
— Ted Petrou (@TedPetrou) April 1, 2020
More cool things built with nbdev 😊 https://t.co/xPMEP9JsN9
— Sylvain Gugger (@GuggerSylvain) March 30, 2020
This is the model from Report 13 of the Imperial College COVID-19 response team. It fits the death data jointly from 11 European countries to estimate the reproduction number and the effect of lockdowns. Such a remarkable piece of @mcmc_stan https://t.co/Hhmbt3KVcQ
— Gilles Louppe (@glouppe) March 30, 2020