Keras是一个用Python编写的深度学习API,运行在机器学习平台TensorFlow之上。

Francois Chollet 5711bc6d3b Add saving v3 integration tests (and fix some minor bugs). 21 hours ago
.devcontainer 147821067a update codespaces bazel install 6 months ago
.github 02b800fa23 build: harden format.yml permissions 2 months ago
.vscode 898622a421 added vscode settings.json to help lint and format the code. 3 months ago
keras 5711bc6d3b Add saving v3 integration tests (and fix some minor bugs). 21 hours ago
shell 43c52e4790 Make OSS scripts to be executable. 6 months ago
third_party f3f23fb6f5 Internal change 1 year ago
.bazelrc 9f671d06d3 Cleanup the bazelrc and remove unrelated items to keras. 1 year ago
.gitignore 5513cf1e73 gitignore .DS_Store 8 months ago
BUILD 373ad97c72 Copy image utils from keras_preprocessing directly into core keras 9 months ago
CONTRIBUTING.md 2e88fa8360 Add the docstring style guide. 1 week ago
ISSUE_TEMPLATE.md 216da11938 Add issue template for keras-team/keras. 1 year ago
LICENSE ac893d1fa7 Change the `LICENSE` file to be a verbatim copy of the complete Apache 2.0 license: 10 months ago
README.md 70079c7132 Update README.md 4 months ago
WORKSPACE bffa122660 Bump zlib to 1.2.13. 1 month ago
requirements.txt b6a3e8edac Change to use the same version of scipy & numpy as TF. 2 months ago
setup.cfg bffc22f612 Make formatting and linting scripts more flexible. 2 months ago

README.md

Keras: Deep Learning for humans

Keras logo

This repository hosts the development of the Keras library. Read the documentation at keras.io.

About Keras

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. Being able to go from idea to result as fast as possible is key to doing good research.

Keras is:

  • Simple -- but not simplistic. Keras reduces developer cognitive load to free you to focus on the parts of the problem that really matter.
  • Flexible -- Keras adopts the principle of progressive disclosure of complexity: simple workflows should be quick and easy, while arbitrarily advanced workflows should be possible via a clear path that builds upon what you've already learned.
  • Powerful -- Keras provides industry-strength performance and scalability: it is used by organizations and companies including NASA, YouTube, and Waymo.

Keras & TensorFlow 2

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:

  • Efficiently executing low-level tensor operations on CPU, GPU, or TPU.
  • Computing the gradient of arbitrary differentiable expressions.
  • Scaling computation to many devices, such as clusters of hundreds of GPUs.
  • Exporting programs ("graphs") to external runtimes such as servers, browsers, mobile and embedded devices.

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.


First contact with Keras

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 Sequential model:

from tensorflow.keras.models import Sequential

model = Sequential()

Stacking layers is as easy as .add():

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 .compile():

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 GradientTape:

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:


Installation

Keras comes packaged with TensorFlow 2 as tensorflow.keras. To start using Keras, simply install TensorFlow 2.


Release and compatibility

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 of the tf-nightly releases (e.g. keras-nightly==2.7.0.dev2021100607 should be used with tf-nightly==2.7.0.dev2021100607). 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.

Keras release Note Compatible Tensorflow version
2.4 Last stable release of multi-backend Keras < 2.5
2.5-pre Pre-release (not formal) for standalone Keras repo >= 2.5 < 2.6
2.6 First formal release of standalone Keras. >= 2.6 < 2.7
2.7 (Upcoming release) >= 2.7 < 2.8
nightly tf-nightly

Support

You can ask questions and join the development discussion:


Opening an issue

You can also post bug reports and feature requests (only) in GitHub issues.


Opening a PR

We welcome contributions! Before opening a PR, please read our contributor guide, and the API design guideline.