Content Overview Who should use Keras
Keras API components
Layers
Models
Other APIs and tools
Next steps Who should use Keras Keras API components Layers Models Other APIs and tools Next steps Keras is the high-level API of the TensorFlow platform. It provides an approachable, highly-productive interface for solving machine learning (ML) problems, with a focus on modern deep learning. Keras covers every step of the machine learning workflow, from data processing to hyperparameter tuning to deployment. It was developed with a focus on enabling fast experimentation. Keras With Keras, you have full access to the scalability and cross-platform capabilities of TensorFlow. You can run Keras on a TPU Pod or large clusters of GPUs, and you can export Keras models to run in the browser or on mobile devices. You can also serve Keras models via a web API. Keras is designed to reduce cognitive load by achieving the following goals: Offer simple, consistent interfaces.
Minimize the number of actions required for common use cases.
Provide clear, actionable error messages.
Follow the principle of progressive disclosure of complexity: It's easy to get started, and you can complete advanced workflows by learning as you go.
Help you write concise, readable code. Offer simple, consistent interfaces. Minimize the number of actions required for common use cases. Provide clear, actionable error messages. Follow the principle of progressive disclosure of complexity: It's easy to get started, and you can complete advanced workflows by learning as you go. Help you write concise, readable code. Who should use Keras The short answer is that every TensorFlow user should use the Keras APIs by default. Whether you're an engineer, a researcher, or an ML practitioner, you should start with Keras. There are a few use cases (for example, building tools on top of TensorFlow or developing your own high-performance platform) that require the low-level TensorFlow Core APIs. But if your use case doesn't fall into one of the Core API applications, you should prefer Keras. TensorFlow Core APIs Core API applications Keras API components The core data structures of Keras are layers and models. A layer is a simple input/output transformation, and a model is a directed acyclic graph (DAG) of layers. layers models Layers The tf.keras.layers.Layer class is the fundamental abstraction in Keras. A Layer encapsulates a state (weights) and some computation (defined in the tf.keras.layers.Layer.call method). tf.keras.layers.Layer Layer tf.keras.layers.Layer.call Weights created by layers can be trainable or non-trainable. Layers are recursively composable: If you assign a layer instance as an attribute of another layer, the outer layer will start tracking the weights created by the inner layer. You can also use layers to handle data preprocessing tasks like normalization and text vectorization. Preprocessing layers can be included directly into a model, either during or after training, which makes the model portable. Models A model is an object that groups layers together and that can be trained on data. The simplest type of model is the Sequential model, which is a linear stack of layers. For more complex architectures, you can either use the Keras functional API, which lets you build arbitrary graphs of layers, or use subclassing to write models from scratch. Sequential The tf.keras.Model class features built-in training and evaluation methods: tf.keras.Model tf.keras.Model.fit: Trains the model for a fixed number of epochs.
tf.keras.Model.predict: Generates output predictions for the input samples.
tf.keras.Model.evaluate: Returns the loss and metrics values for the model; configured via the tf.keras.Model.compile method. tf.keras.Model.fit: Trains the model for a fixed number of epochs. tf.keras.Model.fit tf.keras.Model.predict: Generates output predictions for the input samples. tf.keras.Model.predict tf.keras.Model.evaluate: Returns the loss and metrics values for the model; configured via the tf.keras.Model.compile method. tf.keras.Model.evaluate tf.keras.Model.compile These methods give you access to the following built-in training features: Callbacks. You can leverage built-in callbacks for early stopping, model checkpointing, and TensorBoard monitoring. You can also implement custom callbacks.
Distributed training. You can easily scale up your training to multiple GPUs, TPUs, or devices.
Step fusing. With the steps_per_execution argument in tf.keras.Model.compile, you can process multiple batches in a single tf.function call, which greatly improves device utilization on TPUs. Callbacks. You can leverage built-in callbacks for early stopping, model checkpointing, and TensorBoard monitoring. You can also implement custom callbacks. Distributed training. You can easily scale up your training to multiple GPUs, TPUs, or devices. Step fusing. With the steps_per_execution argument in tf.keras.Model.compile, you can process multiple batches in a single tf.function call, which greatly improves device utilization on TPUs. steps_per_execution tf.keras.Model.compile tf.function For a detailed overview of how to use fit, see the training and evaluation guide. To learn how to customize the built-in training and evaluation loops, see Customizing what happens in fit(). fit fit() Other APIs and tools Keras provides many other APIs and tools for deep learning, including: Optimizers
Metrics
Losses
Data loading utilities Optimizers Optimizers Metrics Metrics Losses Losses Data loading utilities Data loading utilities For a full list of available APIs, see the Keras API reference. To learn more about other Keras projects and initiatives, see The Keras ecosystem. Keras API reference The Keras ecosystem Next steps To get started using Keras with TensorFlow, check out the following topics: The Sequential model
The Functional API
Training & evaluation with the built-in methods
Making new layers and models via subclassing
Serialization and saving
Working with preprocessing layers
Customizing what happens in fit()
Writing a training loop from scratch
Working with RNNs
Understanding masking & padding
Writing your own callbacks
Transfer learning & fine-tuning
Multi-GPU and distributed training The Sequential model The Sequential model The Functional API The Functional API Training & evaluation with the built-in methods Training & evaluation with the built-in methods Making new layers and models via subclassing Making new layers and models via subclassing Serialization and saving Serialization and saving Working with preprocessing layers Working with preprocessing layers Customizing what happens in fit() Customizing what happens in fit() Writing a training loop from scratch Writing a training loop from scratch Working with RNNs Working with RNNs Understanding masking & padding Understanding masking & padding Writing your own callbacks Writing your own callbacks Transfer learning & fine-tuning Transfer learning & fine-tuning Multi-GPU and distributed training Multi-GPU and distributed training To learn more about Keras, see the following topics at keras.io: keras.io About Keras
Introduction to Keras for Engineers
Introduction to Keras for Researchers
Keras API reference
The Keras ecosystem About Keras About Keras Introduction to Keras for Engineers Introduction to Keras for Engineers Introduction to Keras for Researchers Introduction to Keras for Researchers Keras API reference Keras API reference The Keras ecosystem The Keras ecosystem Originally published on the TensorFlow website, this article appears here under a new headline and is licensed under CC BY 4.0. Code samples shared under the Apache 2.0 License. Originally published on the TensorFlow website, this article appears here under a new headline and is licensed under CC BY 4.0. Code samples shared under the Apache 2.0 License. Originally published on the TensorFlow website, this article appears here under a new headline and is licensed under CC BY 4.0. Code samples shared under the Apache 2.0 License. TensorFlow TensorFlow

Walkthroughs, tutorials, guides, and tips. This story will teach you how to do something new or how to do something better.

Keras 101: A Beginner-Friendly Guide to Building Neural Networks

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Untitled Story

A Detailed Overview of TensorFlow Core APIs

Why Being Likable At Work Matters

Windows Sticky Keys Exploit: The War Veteran That Never Dies

Is ‘bias for action’ making product managers lazier?

Zero People Charged With Online Pirating, Swedish Prosecutor's Office Reports

A Detailed Overview of TensorFlow Core APIs

Why Being Likable At Work Matters

Windows Sticky Keys Exploit: The War Veteran That Never Dies

Is ‘bias for action’ making product managers lazier?

Zero People Charged With Online Pirating, Swedish Prosecutor's Office Reports

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps