Early Convolutions Help Transformers See Better
— AK (@ak92501) June 29, 2021
pdf: https://t.co/5XTWUDzFag
abs: https://t.co/Faq0Yi18Bi
convolutional stem in ViT dramatically increases optimization stability and also improves peak performance (by ∼1-2% top-1 accuracy on ImageNet-1k) pic.twitter.com/q0gq67AyuF
CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders
— AK (@ak92501) June 29, 2021
pdf: https://t.co/q7hsXvs6bY
abs: https://t.co/mHP3ZYCYhi
colab: https://t.co/igsVWKntOq pic.twitter.com/uEANOUp5E6
Excited to release Meerkat, a new data library for interactive machine learning! We've (@jundesai, @EyubogluSabri, @HazyResearch) been building this up over the last couple of months.
— Karan Goel (@krandiash) June 29, 2021
Read our blog post to learn more: https://t.co/YCofjOxRz1
This tutorial will introduce compute and data-efficient transformers and provide a step-by-step to create your own Vision Transformers. Through this guide, you'll be able to train state of the art results for classification in both computer vision & NLP. https://t.co/d3bc7ijeBJ
— PyTorch (@PyTorch) June 28, 2021
Sentence Transformers v2 is out and it's fully integrated to the Hub! 🤩
— Hugging Face (@huggingface) June 28, 2021
- Over 90 pretrained models at https://t.co/MF3u2x3cCA
- Widgets and Inference API for sentence embeddings and sentence similarity.
- A lot more!
Read all about it in this blog posthttps://t.co/aXYtSta6g0 pic.twitter.com/uHMqRJTk1M
Single Image Texture Translation for Data Augmentation
— AK (@ak92501) June 28, 2021
pdf: https://t.co/pAWU2Kn0PL
abs: https://t.co/krjNbyN8em
project page: https://t.co/h1xKObA9Do pic.twitter.com/8fya7pYEh8
Visualizer for neural network, deep learning, and machine learning models https://t.co/RZsOfuYpnw #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #tensorflow
— TensorFlow Best Practices (@TFBestPractices) June 28, 2021
Map shows the 15 countries (apart from Sweden) in which the people who currently live in Sweden were born. The Swedish banana reaches down all the way to Thailand. Source: https://t.co/dBGOmLhMsg pic.twitter.com/pUI991GC8e
— Simon Kuestenmacher (@simongerman600) June 27, 2021
📊 Revisiting @hadleywickham's "A Layered Grammar of Graphics" this morning, which gives insight into the theoretical underpinnings of ggplot2:https://t.co/1ejkGYHWnS
— 👩💻 Paige Bailey #BlackLivesMatter (@DynamicWebPaige) June 27, 2021
The recreation of Minard's March on Russia visualization (in just a few lines of code!) gets me every time. 🤯 pic.twitter.com/hP4XAZrS0H
To help reduce gender bias in neural machine translations, we are releasing the Translated Wikipedia Biographies dataset, which can be used to evaluate the gender accuracy of translation models. Learn more and check out the dataset ↓ https://t.co/ldDrLxPa4X
— Google AI (@GoogleAI) June 24, 2021
I'm unreasonably excited about this feature @qlhoest just added to 🤗Datasets
— Thomas Wolf (@Thom_Wolf) June 24, 2021
Seeing a training on a +80GB text corpus –like @oscarnlp– start instantly without waiting for data download/processing has something magical to it🧙♂️
On master at (release soon) https://t.co/AeUFPs26z4 pic.twitter.com/tCw6lFldG5
Takeaway from @karpathy's CVPR talk:
— Chip Huyen (@chipro) June 24, 2021
The most successful ML projects in prod (Tesla, iPhone, Amazon drones, Zipline) are where you own the entire stack.
They iterate not just ML algorithms but also:
- how to collect/label data
- infrastructure
- hardware ML models run on
