Keras - bobbae/gcp GitHub Wiki


Introduction

Keras is the high-level API of Tensorflow 2. Keras is an awesome library that wraps the efficient numerical computation libraries Theano and TensorFlow. Keras is a higher-level deep learning framework, which abstracts many details away, making code simpler and more concise than in PyTorch or Tensorflow, at the cost of limited hackability.

https://keras.io/getting_started/

Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow. It was developed with a focus on enabling fast experimentation. It abstracts away the computation backend, which can be Tensorflow, Theano or CNTK. It does not support a PyTorch backend. It allows you to define and train neural network models in just a few lines of code.

https://cloud.google.com/ai-platform/docs/getting-started-keras

Video

https://www.youtube.com/watch?v=J6Ok8p463C4

Examples

https://keras.io/examples/

Tensorflow Estimator

https://www.youtube.com/watch?v=YCXFceVKHTk

Keras vs Others

https://keras.io/why_keras/

Notebook

https://github.com/GoogleCloudPlatform/cloudml-samples/blob/master/notebooks/Tensorflow/getting-started-keras.ipynb

https://github.com/GoogleCloudPlatform/cloudml-samples/blob/master/notebooks/keras/TextClassificationUsingKerasAndCMLE.ipynb