Neural Style Transfer: 50 Shades of Miaw with @TensorFlow 2.1, via @trinilearn. This is art. ✨https://t.co/tgQWjiccYH pic.twitter.com/pryVDZaBUy
— 👩💻 DynamicWebPaige (@DynamicWebPaige) January 23, 2020
Neural Style Transfer: 50 Shades of Miaw with @TensorFlow 2.1, via @trinilearn. This is art. ✨https://t.co/tgQWjiccYH pic.twitter.com/pryVDZaBUy
— 👩💻 DynamicWebPaige (@DynamicWebPaige) January 23, 2020
2.1 is out 👍
— Josh Gordon (@random_forests) January 9, 2020
Notable features:
- The experimental TextVectorization layer allows you to include your text processing logic inside your model (for cleaner deployment & serialization)
- The standard TF pip package now includes GPU support by default https://t.co/7b2SadvcdC
💥Check this out! 😱@vykthur built this interactive visualization of autoencoders used to classify ECG data using #tensorflow-js.
— TensorFlow (@TensorFlow) January 7, 2020
See it here → https://t.co/ZJEgpVZSTO pic.twitter.com/lmv4hB1Etu
📢 Blazeface is now available in browsers with TensorFlow.js!
— TensorFlow (@TensorFlow) January 6, 2020
The model detects faces and facial features in real-time 👨👩⏰
Try it out now → https://t.co/Km66lDh5R6 pic.twitter.com/3YAM7pBDGY
TensorFlow has a suite of tools for optimizing your models for faster inference: https://t.co/h3qichyArj
— François Chollet (@fchollet) January 6, 2020
This includes post-training weight quantization, and gradual weight pruning during training for your Keras models. pic.twitter.com/rN5o2516wL
Looks useful: Keras-OCR (3rd-party package) provides out-of-the-box OCR models and an end-to-end training pipeline to build new OCR modelshttps://t.co/q7rN49VjvD
— François Chollet (@fchollet) January 4, 2020
We’re excited to release the Alpha of our WebAssembly backend for TensorFlow.js! 🎉
— TensorFlow (@TensorFlow) December 20, 2019
WASM has wider device support and better numerical stability while getting competitive with WebGL for smaller models.
Share your feedback here → https://t.co/PqwNOGDRKZ pic.twitter.com/f5NthyUcHe
tfhub: R interface to TensorFlow Hub - https://t.co/SLoJC6BlmC #rstats pic.twitter.com/yqMWWHDzSa
— RStudio (@rstudio) December 19, 2019
We have a brand new guide on using Mixed Precision in TensorFlow 2.1: https://t.co/xdG7kOKXhh
— François Chollet (@fchollet) December 17, 2019
Speed up training and inference on GPU by up to 3x (and up to 50% on TPU)
A clean TensorFlow 2 implementation of StyleGAN 2 (with pretrained weights for generating landscapes) https://t.co/CT7RknBsQK pic.twitter.com/MuUQZ2mlfw
— François Chollet (@fchollet) December 16, 2019
Courses 1 & 2 of @deeplearningai_‘s newest Specialization is now available on @Coursera! Training a model is only one step in building a working AI system. These courses teach you how to navigate some key deployment scenarios. Enroll here: https://t.co/iVWrTi8QGD pic.twitter.com/ifzwCpFbUK
— Andrew Ng (@AndrewYNg) December 11, 2019
As promised, we have made the Text-To-Text Transfer Transformer (T5) models much easier to fine-tune for new tasks, and we just released a Colab notebook where you can try it yourself on a free TPU!
— Adam Roberts (@ada_rob) December 9, 2019
👇 https://t.co/l6eI88Ih3f
(1/3) pic.twitter.com/LU5scmhbIs