A Keras implementation of BERT -- a new transformer architecture with strong performance across a range of language tasks. https://t.co/OznxM3h51Y
— François Chollet (@fchollet) October 30, 2018
A Keras implementation of BERT -- a new transformer architecture with strong performance across a range of language tasks. https://t.co/OznxM3h51Y
— François Chollet (@fchollet) October 30, 2018
A beginner's guide to image classification by @risin_developer. We especially love this excerpt: "we can use Kaggle kernels which gives more compute power, access to a GPU, and almost all the libraries for machine learning..." | Read it here: https://t.co/ASWKbTkQ8w
— Kaggle (@kaggle) October 29, 2018
This text classification example from TensorFlow.js (train a model locally in Keras, deploy it in the browser) is excellent: https://t.co/hrrVpRgxEF
— Josh Gordon (@random_forests) October 29, 2018
Playing Mortal Kombat with TensorFlow.js https://t.co/taRHHqblOC
— François Chollet (@fchollet) October 25, 2018
Training ML models takes time and losing your weight values can happen at the touch of CTRL-C. In this #CodingTensorFlow @MagnusHyttsten shows you how to load and save models at every epoch so you never lose time or data.
— TensorFlow (@TensorFlow) October 25, 2018
Watch here → https://t.co/LKrQBKSNhY pic.twitter.com/Ihum7i4hxG
How to build your own AlphaZero using Keras https://t.co/HnWpVYZByI
— François Chollet (@fchollet) October 22, 2018
Keras implementation of DeepLabV3+ for image segmentation: https://t.co/LtI5EALWWG pic.twitter.com/6vXUkKSTQS
— François Chollet (@fchollet) October 22, 2018
Eager Execution Enabled
— Zaid Alyafeai (زيد اليافعي ) (@zaidalyafeai) October 13, 2018
In this notebook I explain different concepts in eager execution. I go over variables, ops, gradients, custom gradients, callbacks, metrics and creating models with tf.keras and saving/restoring them. https://t.co/CLUsY2wVDI pic.twitter.com/iQgVEHr7Bi
Noise2Noise: Learning Image Restoration without Clean Data - Official TensorFlow implementation of the ICML 2018 paper https://t.co/Lj5Ka9WsxB #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #tensorflow
— TensorFlow Best Practices (@TFBestPractices) October 11, 2018
This is a great post. "If you’re asking “Keras vs. TensorFlow”, you’re asking the wrong question"https://t.co/irBp1nkdRf https://t.co/QgNukwPw70
— François Chollet (@fchollet) October 8, 2018
To clarify : I'm excited about the direction tf2 is taking. They've made some tough but important decisions and I think tf2 is likely to be great. And I like Geron's book, and his summary here of tf2.
— Jeremy Howard (@jeremyphoward) October 5, 2018
I just think the "better than pytorch" claim is poorly made here. https://t.co/HDvcrUzg7q
TPUs are now in early alpha on Colab! The linked example shows how to train a tf.keras model on a TPU, with a few lines of additional code. Appreciate the efforts to make this easy. It's a good sign. In the future, the easy way will be the fast way. https://t.co/WmZkVfFjBw
— Josh Gordon (@random_forests) October 4, 2018