Announcing https://t.co/fuWTPxe9I1 release 0.8. Runnable on AWS Sagemaker and Google Colab. Major changes are a full rewrite of the NLP chapters, pretraining, byte pair encoding, BERT, and lots of fine-tuneing. Stay tuned for a surprise next week.https://t.co/9jv3KVlmDs
— Alex Smola (@smolix) May 30, 2020
Nice/fun YouTube channel walking through recent papers in deep learning in a video format, this episode on GPT-3. Cool! :) https://t.co/9QyKkgSH8Q
— Andrej Karpathy (@karpathy) May 29, 2020
Simpsons Paradox https://t.co/eZ2bbpDzwV pic.twitter.com/RogwBZv2V3
— Chris Albon (@chrisalbon) May 22, 2020
Check out d2l-book, a better toolkit for building Jupyter books. Websites, Jupyter notebooks, PDF books and code documentation all in one place (courtesy of Mu Li). Check it out https://t.co/WtdVVvkwrB
— Alex Smola (@smolix) May 19, 2020
Use @plotlygraphs Dash, @rapidsai, and #Datashader to build interactive #dataviz dashboards that render large scale datasets of 300 million+ rows using #GPUs. Walkthrough how we made a demo using #Census data. https://t.co/yQ5s4bUaGc
— RAPIDS AI (@rapidsai) May 19, 2020
New tutorial!🚀
— Adrian Rosebrock (@PyImageSearch) May 18, 2020
Image inpainting with #OpenCV and #Python
- Restore old, degraded photos
- Repair damaged photos
- Mask/remove objects
Full tutorial w/ source code:https://t.co/lHYlMqbi5Y 👍#ComputerVision #MachineLearning #ArtificialIntelligence #AI #DataScience pic.twitter.com/zIxmXjloyQ
I can think of hundreds of data augmentation strategies for CV, eg https://t.co/JsGj2fRNMa
— Reza Zadeh (@Reza_Zadeh) May 18, 2020
For NLP tasks, there's only a handful, eg https://t.co/aRQiZrh5N3
NLP data is far more brittle.
New content on https://t.co/m6mT8SrKDD: Keras debugging tips.https://t.co/iUf4sYbsyC
— François Chollet (@fchollet) May 16, 2020
Projects are THE BEST way to pick up data science and applied machine learning, but choosing a project can be tough. If you’re stuck, I wrote this for you.https://t.co/tDJOP9li7Y
— Brandon Rohrer (@_brohrer_) May 16, 2020
By the way, we just updated 𝗢𝗨𝗥 𝗗𝗘𝗙𝗜𝗡𝗜𝗧𝗜𝗩𝗘 𝗧𝗨𝗧𝗢𝗥𝗜𝗔𝗟 🔥 to training a new language model from scratch.
— Julien Chaumond (@julien_c) May 16, 2020
Updated Colab notebook with the new Trainer =)
➡️ https://t.co/nGQxwqwwZu pic.twitter.com/h392FC7FhZ
Kaggler reigHns has created a great notebook with helpful code snippets that can be used in plotting bounding boxes on images in grids as part of our Global Wheat Detection competition: https://t.co/GP6vZKLmXV pic.twitter.com/Zj9rLu4mcA
— Kaggle (@kaggle) May 14, 2020
🙌 A responsible-scraping-centric code through…
— Mara Averick (@dataandme) May 14, 2020
⚽️ "Intro to {polite} Web Scraping of Soccer Data with R!" by @R_by_Ryo https://t.co/GTvXhOJycg #rstats
