//=time() ?>
#30DayMapChallenge ~ Green & Yellow
For the 7th and 8th entries, I visualised observations of whales around the world and soybean production by country
The dataset about the🐳is quite interesting, I would have liked to work more with it. I had to rush to avoid falling behind😂
A fully interactive CG toolset that not enough junior artists know about- https://t.co/1CTllQAW1n - Clarisse iFX is built by artists for artists, it is designed to simplify today’s complex creative workflows, empowering users with interactivity, speed and power over datasets cont
Egok360: A 360 Egocentric Kinetic Human Activity Video Dataset. https://t.co/oPe9wylkJ7
Some fun ones from a really tiny dataset (475 images)
At the time I forgot to share an interp of the final model from the @natlibscot @CreateInf project. Trained on ~900 imgs of geological surveys from @natlibscotmaps. Smaller dataset than the others, you can see it’s a little nervous.
After many, many months, @AydaoGMan has finally cracked “stylegan on complex datasets”. Look how good these are! Trained on 2M danbooru photos, I think.
I can’t overstate how much work this took. There are so many variants to try that I basically gave up.
Recently joined the #infohackit online design course for researchers! Here's my first attempt at an infographic using a previous dataset from TidyTuesday - think my penguin is a Gentoo! Next stop, creating some visuals for my PhD research... #scicom #datavis
Wanted to see what hapens when I fine tune @theshawwn's model.ckpt-533504.pkl upon a dataset of Muppet-Faces. Well, adorable monsters happen. Here are four of them from the 37Kimg fine-tuning checkpoint. Samples were then processed with Artomaton's Pastel filter.
My #PranksyLand build is a podium with 7 of my artworks showcased. These were AI generated (StyleGAN) from a custom water-colour dataset that I curated. Do read about the full project at:
https://t.co/PMlb8TC4SO
Thanks @pranksyNFT my friend for this opportunity.
@cryptovoxels
almost a year since i noticed the trend it's accelerating:
training on your own datasets it's not sufficient anymore - even if you dont' copy other you start copying yourself
The third dimension - Ideas/Concepts is even more important
SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing. https://t.co/mnhBmP71bc
DanbooRegion: Illustration and Cartoon Region Dataset Annotated by Real-life Artists
github: https://t.co/o2lQj2mnqv
a couple favs from a model i'm training on another generative dataset from @dmitricherniak
checkerboard remains a challenge but as they say we shall never cease from exploration, or whatever
June 2020 temperature anomalies in Arctic Siberia were striking.
The maximum temperature anomaly in ERA5 0.25° gridded data was 10.3°C, which is the highest value in the Northern Hemisphere at any summer month since 1979 (so in the whole dataset).
i’m using topaz lab’s proprietary software ai gigapixel to do the bulk of the upscaling, which has a super-easy-to-use command-line interface. it was trained on another dataset of pictures at various resolutions. it only sees patterns too
Extracting the main trend in a dataset: the Sequencer algorithm. https://t.co/JZt8kkMm9S
🦠Fight Covid-19 with BERT💊:
I am happy to announce the release of two BERTs further pre-trained on the @kaggle CORD-19 dataset (https://t.co/ezDmtSieBX), namely ClinicalCovidBERT and BioCovidBERT. Both models are on @huggingface. More info on the repo (https://t.co/bhldkv77pT)
Abstract hands
GAN generated hands, trained on a dataset of images from subway-hands Instagram account
#generative #creativecoding #aiart @runwayml
Major update to our #CoronavirusDataset: now featuring >2,200 molecular interactions involving proteins from #SARSCoV2 / #COVID19 virus, #SARS and other members of the Coronaviridae family. Over 40 new publications added since our first release: https://t.co/CO7H2qGqIm