babalu_babs

[Rahul Agarwal @MLWhiz]

Want to learn Pytorch?
Read the full article: The Most Complete Guide to PyTorch for Data Scientists
▸ https://t.co/FrIimLAuAa

#Datascience #Machinelearning #Statistics #Python

[FastAPI @FastAPI]

The FastAPI Deployment guide was just revamped ✨

https://t.co/GKh2WHjx9U

💡 Deployment Concepts: https://t.co/egm4UfNUAN
👩‍🏭 Gunicorn with Uvicorn: https://t.co/GfgmxH23oE
🐋 FastAPI in Containers and Kubernetes: https://t.co/9FAqTwhBYB

[Even Oldridge @Even_Oldridge]

Want to learn about embeddings in recommender systems and how to distribute them across multiple GPUs? Check out this great article about how unique techniques for training in our custom framework HugeCTR have been adapted to Tensorflow: https://t.co/A2YNT46aUR

[Mohit Shridhar @mohito1905]

5/
And unlike traditional ‘object detectors’, CLIP is not restricted to a predefined set of classes, or a top-down pipeline that requires bounding boxes or instance segmentations. Try it out yourself with @kevin_zakka ’s CLIP Colab: https://t.co/8BIjPQcxHO

[Even Oldridge @Even_Oldridge]

Incredibly excited and proud to share work by the @nvidiaai Merlin team at #RecSys2021. We introduce an open source library which wraps @huggingface transformers library and makes it accessible for session-based RecSys. Our blog has all the details: https://t.co/07pwGMTfhV

[Scott Condron @_ScottCondron]

If you want to learn about GitHub Actions, here’s a tutorial by @jeremyphoward to use ghapi, a Python wrapper for the @github API, and Github Actions.

It shows how to reply “thank you” to all PRs, then shows how to run a scheduled multi-job workflow 🤩

https://t.co/pzufSBA5lp

[Awesome Go Repositories @GolangRepos]

LeetCode-in-Go: Go Solution for LeetCode algorithms problems, 100% coverage.
⭐️ 2727
#golang
https://t.co/B5iHzUlNq8

[lak lakshmanan @lak_luster]

Very accessible article explaining what the challenges in large scale ML are. And why many of the model optimization methods have limited promise. Highly recommend.
https://t.co/96TFV1XrUj

[Pete Skomoroch @peteskomoroch]

Many companies struggle to get impact from machine learning projects, so @mikeloukides and I wrote this guide: "What you need to know about product management for AI" https://t.co/45kfIFYVTA

[Gus (🤖🧠+🐍+🥑🗣️) @gusthema]

This is incredible!

The generated translation is voiced on the same voice of who spoke with a zero shot learning.

This means that it can:
- translate what you say
- speak it back to you with your own voice!!! 🤯🤯
- without any additional training

Very cool!

[Sayak Paul @RisingSayak]

In our latest #GCP blog, @algo_diver & I dig deep into a dual deployment pipeline.

We introduce three new custom components in #TFX & utilize a good chunk of #ML ecosystem provided by Google - #Keras, @googlecloud, @TensorFlow, etc.

Blog: https://t.co/tg7UjNuhn5

[Awni Hannun @awnihannun]

Just added the second half of "An Introduction to Weighted Automata in Machine Learning", available here https://t.co/B0uZumojIl

Comments, feedback, typos encouraged!

[Krishna Srinivasan @krishna2]

We are very happy to announce WIT: Wikipedia-Based Image Text Dataset, a large multimodal multilingual dataset. @GoogleAI

https://t.co/OiHKIiVL2f

[Jure Leskovec @jure]

It was great to host the Stanford Graph Learning workshop. Humbled to receive an amazing
response from the community---over 7000 attendees. Slides and videos are available at:
https://t.co/bgc7UTbuhB Make sure to check out https://t.co/AWowrGc4uR as well!

[Stanford AI Lab @StanfordAILab]

Interested in automatically fixing your code, or in breaking other people's code realistically? In our latest post, @michiyasunaga describes BIFI, an unsupervised approach that learns how to do both at the same time to repair code better. Check it out! https://t.co/Kt7PflJgxI

[Google AI @GoogleAI]

Multimodal visio-linguistic models rely on rich datasets to model the relationship between images and text—today we introduce a new large multimodal dataset that is multilingual and the first to include contextual fields. Learn more about how it was built↓https://t.co/LsAJtxEiMF

[Jesse Engel @jesseengel]

It’s well known that neural networks model correlation and not causation.

Recently, I’ve found it helpful to think about NN blocks as literal correlations of correlations of correlations …

(incl. dense, norm, nonlin, conv, softmax, transformer, LMs, GANs, …)

🧵 1/20

[Philip Vollet @philipvollet]

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

https://t.co/1LHx9MTn7G

[lak lakshmanan @lak_luster]

Waze standardizes on Tensorflow, TFX, and Vertex AI Pipelines. Fully managed services. Data scientists have to deal with only Python but are in the project end-to-end.

https://t.co/3Mhw2xPGpW

[Google AI @GoogleAI]

As #NeuralNetwork models and training data size grow, training efficiency has become more important. Today we present two families of models for image recognition that train faster and achieve state-of-the-art performance. Learn more and grab the code ↓ https://t.co/pG1rECOVoL