Keras

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, Theano and many more.

[Aakash Kumar Nain @A_K_Nain]

How quickly can we build a captcha reader using deep learning? Check out yourself the Captcha cracker built @TensorFlow 2.0 and #Keras
https://t.co/aOvVotwQP5

[François Chollet @fchollet]

Keras turns 4 years old today 🎂

Congrats to all contributors and the entire community! We're only just getting started 👍

[Keras @kerasteam]

Working with TensorFlow 2.0 Alpha:

https://t.co/r3hzktQyRv

[Taeyoung Kim @tykimo]

We used an artificial intelligence model to generate the backside magnetogram of the Sun and our work was listed in Nature Astronomy. Of course, the model is implemented as Keras. Thanks to @fchollet and Keras that helped me get into deep learning easily.

[François Chollet @fchollet]

Researchers are using Keras & TensorFlow to automatically transcribe hundreds of thousands of ancient manuscripts from the Vatican secret archives. Learn more: https://t.co/7TmhFj7Jrg

[François Chollet @fchollet]

Using Keras for "thought reading" (subvocalized word classification from EEG signals): https://t.co/sNPoUh9aHp 🧠

[François Chollet @fchollet]

As of Feb 2019, I think we are still not near peak Deep Learning.

Peak hype? That was around 2016-2017.

Peak applications & deployment? We have a long way to go. We're still expanding fast. The Keras userbase grew 35% last year, and will likely grow at least as much in 2019.

[François Chollet @fchollet]

Using Keras to automate supernovas identification, potentially cutting in half the time it would take astronomers to discover supernovas: https://t.co/nTTiqDudX8

[Lex Fridman @lexfridman]

New @TensorFlow tutorial on "deep learning basics" is up on our GitHub repo including image classification demonstrated on a beautiful MNIST dream that @hardmaru once had. GitHub: https://t.co/IoKxsgtygU

[TodaYWasAgainNothingToday @totti0223]

As working in the fields of plant science and agriculture as a “relatively wet” bioinformatician, feeling the increasing needs of tutorial specialized for plant biology in addition to CIFAR-10 and MNIST to give biologists a better implementation of what they can do with DL.

[François Chollet @fchollet]

Desnapify: cool project about training a pix2pix-like model to remove Snapchat filters from pictures https://t.co/H2hWAQmBKM

[TensorFlow @TensorFlow]

Take a sneak peek into TensorFlow 2.0’s new features!

Learn more here ↓ https://t.co/NQAsvxT9g2

[TensorFlow @TensorFlow]

In this guest article, @Sam_Witteveen covers how to run Keras on TPUs for free in Colab!

Read how here ↓ https://t.co/SaLwDRlGn0

[François Chollet @fchollet]

Very well-explained post on designing an audio ad-blocker -- the best solution uses a combination of audio fingerprinting with acoustic classification using Keras LSTMs over Mel-spectrograms https://t.co/k0bpdGdqVr

[PyImageSearch @PyImageSearch]

New tutorial!🚀 Auto-Keras and AutoML: A Getting Started Guide
- Automatically create + train #DeepLearning models
- Zero hyperparameters to tune
- State-of-the-art results
Check out the full tutorial (w/ code) here: https://t.co/hvAVWUeiAr 👍 #Python #MachineLearning #Keras

[Martin Görner @martin_gorner]

Here is an end-to-end canonical sample for training a model on Cloud TPUs in Keras. It has full code for loading the data from scratch using https://t.co/wE2Mjy7ETU.Dataset and also exporting the trained model to ML Engine for inference. Colab notebook: https://t.co/RIpkluc09d

[hardmaru @hardmaru]

A Keras Implementation of Sketch-RNN! @Polly_zk trained his Keras model on the QuickDraw Guitar and Guitar+Cat classes which were not included in the official release. 🖍 https://t.co/Lasn7lDqUW

[François Chollet @fchollet]

Just noticed that the Keras repo has more stars than the Bitcoin repo (37.1k vs 36.6k) 🌟 Nice

[François Chollet @fchollet]

2018 was a year of exceptional growth and consolidation for Keras and TensorFlow. I'm planning for 2019 to be even better 😊