TF 2.1 is coming soon (RC0 out now), with extended TPU support: https://t.co/aqv7xTB2Bu (via @martin_gorner)
— François Chollet (@fchollet) December 6, 2019
TF 2.1 is coming soon (RC0 out now), with extended TPU support: https://t.co/aqv7xTB2Bu (via @martin_gorner)
— François Chollet (@fchollet) December 6, 2019
You can now build and run ML pipelines in an interactive Colab notebook using TensorFlow Extended (TFX)! 📓
— TensorFlow (@TensorFlow) November 25, 2019
Develop in a notebook and then export to a production-ready ML pipeline.
Try it in your browser today → https://t.co/6T034jsRV3 pic.twitter.com/e9IcEoUJdy
Built-in losses and metrics in Keras follow the signature `loss(y_true, y_pred, sample_weight=None)`. If you have exotic losses or metrics, a simple way to add them w/o having to implement your own training loop from scratch is to define them in an "endpoint layer". Like this: pic.twitter.com/UILTVriiuf
— François Chollet (@fchollet) November 25, 2019
Generate images with Tensorflow 2 and GANs https://t.co/a9FVnYFO4x #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #tensorflow
— TensorFlow Best Practices (@TFBestPractices) November 24, 2019
BodyPix 2.0 has been released, including multi-person segmentation support and a new live demo!
— TensorFlow (@TensorFlow) November 18, 2019
To learn more, read the post by @tylerzhu3, @oveddan, @greenbeandou, @dsmilkov, @karlssonper, @ire_alva, @nsthorat.
Details here → https://t.co/Zq8dwiNO5A pic.twitter.com/a4qKJu9EJ1
New Keras feature: the TextVectorization layer. It takes as input strings and takes care of text standardization, tokenization, and vocabulary indexing.
— François Chollet (@fchollet) November 18, 2019
This enables you to create models that process raw strings.
End-to-end text classification example: https://t.co/xPAw4FIY2b pic.twitter.com/FxCiTRbJU5
Tensorflow for R: Variational convnets with tfprobability https://t.co/wMHh79mlRX #rstats #rkeras pic.twitter.com/aKTcnqRNfX
— RStudio (@rstudio) November 13, 2019
Spleeter is an amazing open-source project from Deezer (the French Spotify) that uses Deep Learning to do source separation on musical tracks. Built with Keras and TensorFlow. It runs out-of-the-box on CPU!
— François Chollet (@fchollet) November 5, 2019
Blog post: https://t.co/TWCciDjPAS
Code: https://t.co/Cx8EpApSqA pic.twitter.com/5Xu8Lldwy9
New tutorial!🚀 Traffic Sign Classification with #Keras and #TensorFlow 2.0 🛑🚦⚠️
— Adrian Rosebrock (@PyImageSearch) November 4, 2019
- 95% accurate
- Includes pre-trained model
- Full tutorial w/ #Python codehttps://t.co/MkWiTaYKwU 👍#DeepLearning #MachineLearning #ArtificialIntelligence #DataScience #AI pic.twitter.com/20jYvQw7Dw
I'm really happy w/ caching in https://t.co/14p1S1Pup6. Have expensive preprocessing in your pipeline?
— Josh Gordon (@random_forests) November 2, 2019
ds = tf.data.Dataset.list_files('images/*')
ds = ds.map(load_and_preprocess)
A cache lets you pay for that just once. The speedup is dramatic, and takes one LOC.
Example:
The team at @Deezer just released #Spleeter, a Python music source separation library with state-of-the-art pre-trained models! 🎶✨
— 👩💻 DynamicWebPaige @ #TFWorld 🌍 (@DynamicWebPaige) November 2, 2019
Straight from command line, you can extract voice, piano, drums... from any music track! Uses @TensorFlow and #Keras.https://t.co/e4lyVtT2lR pic.twitter.com/tDsBMSYiJD
Keras Tuner is now out of beta! v1 is out on PyPI.https://t.co/riqnIr4auA
— François Chollet (@fchollet) October 31, 2019
Fully-featured, scalable, easy-to-use hyperparameter tuning for Keras & beyond. pic.twitter.com/zUDISXPdBw