► Code examples

Code examples

Our code examples are short (less than 300 lines of code), focused demonstrations of vertical deep learning workflows.

All of our examples are written as Jupyter notebooks and can be run in one click in Google Colab, a hosted notebook environment that requires no setup and runs in the cloud. Google Colab includes GPU and TPU runtimes.

★

= Good starter example

= Keras 3 example

Computer Vision

Natural Language Processing

Text classification

★

Text classification from scratch

Review Classification using Active Learning

Text Classification using FNet

Large-scale multi-label text classification

Text classification with Transformer

Text classification with Switch Transformer

Text classification using Decision Forests and pretrained embeddings

Using pre-trained word embeddings

Bidirectional LSTM on IMDB

Data Parallel Training with KerasHub and tf.distribute

Machine translation

English-to-Spanish translation with KerasHub

★

English-to-Spanish translation with a sequence-to-sequence Transformer

Character-level recurrent sequence-to-sequence model

Entailment prediction

Multimodal entailment

Named entity recognition

Named Entity Recognition using Transformers

Sequence-to-sequence

Text Extraction with BERT

Sequence to sequence learning for performing number addition

Text similarity search

Semantic Similarity with KerasHub

Semantic Similarity with BERT

Sentence embeddings using Siamese RoBERTa-networks

Language modeling

End-to-end Masked Language Modeling with BERT

Abstractive Text Summarization with BART

Pretraining BERT with Hugging Face Transformers

Parameter efficient fine-tuning

Parameter-efficient fine-tuning of GPT-2 with LoRA

Other

Training a language model from scratch with 🤗 Transformers and TPUs

MultipleChoice Task with Transfer Learning

Question Answering with Hugging Face Transformers

Abstractive Summarization with Hugging Face Transformers

Structured Data

Structured data classification

★

Structured data classification with FeatureSpace

★

FeatureSpace advanced use cases

★

Imbalanced classification: credit card fraud detection

Structured data classification from scratch

Structured data learning with Wide, Deep, and Cross networks

Classification with Gated Residual and Variable Selection Networks

Classification with TensorFlow Decision Forests

Classification with Neural Decision Forests

Structured data learning with TabTransformer

Recommendation

Collaborative Filtering for Movie Recommendations

A Transformer-based recommendation system

Timeseries

Timeseries classification

★

Timeseries classification from scratch

Timeseries classification with a Transformer model

Electroencephalogram Signal Classification for action identification

Event classification for payment card fraud detection

Anomaly detection

Timeseries anomaly detection using an Autoencoder

Timeseries forecasting

Traffic forecasting using graph neural networks and LSTM

Timeseries forecasting for weather prediction

Generative Deep Learning

Image generation

★

Denoising Diffusion Implicit Models

★

A walk through latent space with Stable Diffusion

DreamBooth

Denoising Diffusion Probabilistic Models

Teach StableDiffusion new concepts via Textual Inversion

Fine-tuning Stable Diffusion

Variational AutoEncoder

GAN overriding Model.train_step

WGAN-GP overriding Model.train_step

Conditional GAN

CycleGAN

Data-efficient GANs with Adaptive Discriminator Augmentation

Deep Dream

GauGAN for conditional image generation

PixelCNN

Face image generation with StyleGAN

Vector-Quantized Variational Autoencoders

Style transfer

Neural style transfer

Neural Style Transfer with AdaIN

Text generation

★

GPT2 Text Generation with KerasHub

GPT text generation from scratch with KerasHub

Text generation with a miniature GPT

Character-level text generation with LSTM

Text Generation using FNet

Graph generation

Drug Molecule Generation with VAE

WGAN-GP with R-GCN for the generation of small molecular graphs

Other

A walk through latent space with Stable Diffusion 3

Density estimation using Real NVP

Audio Data

Speech recognition

Automatic Speech Recognition with Transformer

Other

Automatic Speech Recognition using CTC

MelGAN-based spectrogram inversion using feature matching

Speaker Recognition

Audio Classification with the STFTSpectrogram layer

English speaker accent recognition using Transfer Learning

Audio Classification with Hugging Face Transformers

Reinforcement Learning

Actor Critic Method

Proximal Policy Optimization

Deep Q-Learning for Atari Breakout

Deep Deterministic Policy Gradient (DDPG)

Graph Data

Graph attention network (GAT) for node classification

Node Classification with Graph Neural Networks

Message-passing neural network (MPNN) for molecular property prediction

Graph representation learning with node2vec

Quick Keras Recipes

Keras usage tips

Parameter-efficient fine-tuning of Gemma with LoRA and QLoRA

Float8 training and inference with a simple Transformer model

Keras debugging tips

Customizing the convolution operation of a Conv2D layer

Trainer pattern

Endpoint layer pattern

Reproducibility in Keras Models

Writing Keras Models With TensorFlow NumPy

Simple custom layer example: Antirectifier

Packaging Keras models for wide distribution using Functional Subclassing

Serving

Serving TensorFlow models with TFServing

ML best practices

Estimating required sample size for model training

Memory-efficient embeddings for recommendation systems

Creating TFRecords

Other

Approximating non-Function Mappings with Mixture Density Networks

Probabilistic Bayesian Neural Networks

Knowledge distillation recipes

Evaluating and exporting scikit-learn metrics in a Keras callback

How to train a Keras model on TFRecord files

Adding a new code example

We welcome new code examples! Here are our rules:

They should be shorter than 300 lines of code (comments may be as long as you want).
They should demonstrate modern Keras best practices.
They should be substantially different in topic from all examples listed above.
They should be extensively documented & commented.

New examples are added via Pull Requests to the keras.io repository. They must be submitted as a .py file that follows a specific format. They are usually generated from Jupyter notebooks. See the tutobooks documentation for more details.

If you would like to convert a Keras 2 example to Keras 3, please open a Pull Request to the keras.io repository.

Code examples

◆ Adding a new code example

Code examples

Image classification

Image segmentation

Object detection

3D

OCR

Image enhancement

Data augmentation

Image & Text

Vision models interpretability

Image similarity search

Video

Performance recipes

Other

Text classification

Machine translation

Entailment prediction

Named entity recognition

Sequence-to-sequence

Text similarity search

Language modeling

Parameter efficient fine-tuning

Other

Structured data classification

Recommendation

Timeseries classification

Anomaly detection

Timeseries forecasting

Image generation

Style transfer

Text generation

Graph generation

Other

Speech recognition

Other

Keras usage tips

Serving

ML best practices

Other

Adding a new code example