|Ramesh Sampath cdb89b47d1 Align `model.summary`. Fix for long names and nested levels.||5 days ago|
|.devcontainer||3 months ago|
|.github||2 weeks ago|
|.vscode||3 months ago|
|keras||5 days ago|
|shell||9 months ago|
|third_party||1 year ago|
|.bazelrc||6 days ago|
|.bazelversion||3 months ago|
|.gitignore||1 year ago|
|BUILD||1 year ago|
|CONTRIBUTING.md||1 week ago|
|ISSUE_TEMPLATE.md||1 year ago|
|LICENSE||1 year ago|
|README.md||1 month ago|
|WORKSPACE||1 month ago|
|oss_setup.py||4 weeks ago|
|pip_build.py||3 weeks ago|
|requirements.txt||1 month ago|
|setup.cfg||1 month ago|
This repository hosts the development of the Keras library. Read the documentation at keras.io.
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 and providing a delightful developer experience.
The purpose of Keras is to give an unfair advantage to any developer looking to ship ML-powered apps.
TensorFlow 2 is an end-to-end, open-source machine learning platform. You can think of it as an infrastructure layer for differentiable programming. It combines four key abilities:
Keras is the high-level API of TensorFlow 2: an approachable, highly-productive interface for solving machine learning problems, with a focus on modern deep learning. It provides essential abstractions and building blocks for developing and shipping machine learning solutions with high iteration velocity.
Keras empowers engineers and researchers to take full advantage of the scalability and cross-platform capabilities of TensorFlow 2: you can run Keras on TPU or on large clusters of GPUs, and you can export your Keras models to run in the browser or on a mobile device.
The core data structures of Keras are layers and models.
The simplest type of model is the
Sequential model, a linear stack of layers.
For more complex architectures, you should use the Keras functional API,
which allows you to build arbitrary graphs of layers or write models entirely from scratch via subclassing.
Here is the
from tensorflow.keras.models import Sequential model = Sequential()
Stacking layers is as easy as
from tensorflow.keras.layers import Dense model.add(Dense(units=64, activation='relu')) model.add(Dense(units=10, activation='softmax'))
Once your model looks good, configure its learning process with
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
If you need to, you can further configure your optimizer. The Keras philosophy is to keep simple things simple, while allowing the user to be fully in control when they need to (the ultimate control being the easy extensibility of the source code via subclassing).
model.compile(loss=tf.keras.losses.categorical_crossentropy, optimizer=tf.keras.optimizers.SGD( learning_rate=0.01, momentum=0.9, nesterov=True))
You can now iterate on your training data in batches:
# x_train and y_train are Numpy arrays. model.fit(x_train, y_train, epochs=5, batch_size=32)
Evaluate your test loss and metrics in one line:
loss_and_metrics = model.evaluate(x_test, y_test, batch_size=128)
Or generate predictions on new data:
classes = model.predict(x_test, batch_size=128)
What you just saw is the most elementary way to use Keras.
However, Keras is also a highly-flexible framework suitable to iterate on state-of-the-art research ideas. Keras follows the principle of progressive disclosure of complexity: it makes it easy to get started, yet it makes it possible to handle arbitrarily advanced use cases, only requiring incremental learning at each step.
In much the same way that you were able to train & evaluate a simple neural network above in a few lines,
you can use Keras to quickly develop new training procedures or exotic model architectures.
Here's a low-level training loop example, combining Keras functionality with the TensorFlow
import tensorflow as tf # Prepare an optimizer. optimizer = tf.keras.optimizers.Adam() # Prepare a loss function. loss_fn = tf.keras.losses.kl_divergence # Iterate over the batches of a dataset. for inputs, targets in dataset: # Open a GradientTape. with tf.GradientTape() as tape: # Forward pass. predictions = model(inputs) # Compute the loss value for this batch. loss_value = loss_fn(targets, predictions) # Get gradients of loss wrt the weights. gradients = tape.gradient(loss_value, model.trainable_weights) # Update the weights of the model. optimizer.apply_gradients(zip(gradients, model.trainable_weights))
For more in-depth tutorials about Keras, you can check out:
Keras comes packaged with TensorFlow 2 as
To start using Keras, simply install TensorFlow 2.
You can then import Keras as follows:
from tensorflow import keras
Keras has nightly releases (
keras-nightly on PyPI)
and stable releases (
keras on PyPI).
The nightly Keras releases are usually compatible with the corresponding version
keras-nightly==2.7.0.dev2021100607 should be
We don't maintain backward compatibility for nightly releases.
For stable releases, each Keras
version maps to a specific stable version of TensorFlow.
The table below shows the compatibility version mapping between TensorFlow versions and Keras versions.
All the release branches can be found on GitHub.
All the release binaries can be found on Pypi.
You can ask questions and join the development discussion:
You can also post bug reports and feature requests (only) in GitHub issues.
We welcome contributions! Before opening a PR, please read our contributor guide, and the API design guideline.