Exciting to see XNNPack open-sourced: https://t.co/fHKBsQ42Hf - it's a library of optimized floating point arithmetic operations to speed up deep learning calculations on Arm and x86.
— Pete Warden (@petewarden) October 4, 2019
We're already using it in @TensorFlow Lite, I'd love to see it more widely adopted!
An end-to-end tutorial showing how to deploy Keras models on Android via TFLite: https://t.co/QRGYs2EJMP
— François Chollet (@fchollet) October 4, 2019
🗣 Attention #TensorFlow community!
— TensorFlow (@TensorFlow) September 30, 2019
We are excited to announce TensorFlow 2.0. Inspired by all of your feedback, this powerful and easy-to-use framework includes tight Keras integration, expanded TF datasets, and more.
Watch @lmoroney present here → https://t.co/bzI1vDZDnV pic.twitter.com/uoPvOXJnzP
One of my favorite things about TensorFlow 2.0 is that it brings high-level UX and low-level flexibility together fluently.
— François Chollet (@fchollet) September 30, 2019
This is the result of 4 years of watching practitioners and researchers use the product, and thinking about how we can make life better for both.
To get started, check out this tf.keras guide: https://t.co/iaH4Q5Qsvr
— François Chollet (@fchollet) September 30, 2019
In particular "Guide to training and evaluation" and "Guide to writing layers and models from scratch with subclassing" highlights some of the major changes.
TensorFlow 2.0 has been released! Congrats everyone, and thanks for making this possible.
— Josh Gordon (@random_forests) September 30, 2019
Release notes: https://t.co/NSgSiswauO
TF-Explain: model interpretability utilities for tf.keras https://t.co/YFmOHGO3dV
— François Chollet (@fchollet) September 28, 2019
🤗Transformers 2.0💥
— Thomas Wolf (@Thom_Wolf) September 26, 2019
State-of-the-art NLP in TensorFlow 2.0/PyTorch
8 architectures
33 trained models
102 lang.
Seamlessly pick the right framework for training, eval, deploy
Train on TPU ⏩ finetune/test in PyTorch ⏩ serve w. TFX
🍒Keras magic: train SOTA model in 10 lines👇 pic.twitter.com/K7BNdxDBQh
Notebooks implementing real-time trigger word detection in Keras. Neat work :) https://t.co/m9K26H06ss
— François Chollet (@fchollet) September 23, 2019
Let’s get moving!
— TensorFlow (@TensorFlow) September 23, 2019
See how the @olivexai engineering team uses TensorFlow Lite and PoseNet to track body movements and provide a more interactive exercise experience in their app ‘Smart Baduanjin’.
Read the guest blog ↓ https://t.co/5aZIQZVzW9
Attention! TFX 0.14.0 is here 🎉
— TensorFlow (@TensorFlow) September 20, 2019
Create #TensorFlow production ML pipelines with #TFX. Please report any issues in Github.
To install, “pip install tfx” or visit → https://t.co/Nw5DfIKGU0 pic.twitter.com/2dREVSco76
Introducing DeepPavlov: an open-source library for developing dialogue systems and chatbots! Learn more in this guest post from @deeppavlov. #PoweredByTF
— TensorFlow (@TensorFlow) September 18, 2019
Read the blog ↓ https://t.co/qq3Sxycw8v
