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

Computer Vision

Image classification

★

Image classification from scratch

★

Simple MNIST convnet

★

Image classification via fine-tuning with EfficientNet

Image classification with Vision Transformer

Image Classification using BigTransfer (BiT)

Classification using Attention-based Deep Multiple Instance Learning

Image classification with modern MLP models

A mobile-friendly Transformer-based model for image classification

Pneumonia Classification on TPU

Compact Convolutional Transformers

Image classification with ConvMixer

Image classification with EANet (External Attention Transformer)

Involutional neural networks

Image classification with Perceiver

Few-Shot learning with Reptile

Semi-supervised image classification using contrastive pretraining with SimCLR

Image classification with Swin Transformers

Train a Vision Transformer on small datasets

A Vision Transformer without Attention

Image segmentation

★

Image segmentation with a U-Net-like architecture

Multiclass semantic segmentation using DeepLabV3+

Object detection

Object Detection with RetinaNet

Keypoint Detection with Transfer Learning

Object detection with Vision Transformers

3D

3D image classification from CT scans

Monocular depth estimation

3D volumetric rendering with NeRF

Point cloud classification

OCR

★

OCR model for reading Captchas

Handwriting recognition

Image enhancement

Convolutional autoencoder for image denoising

Low-light image enhancement using MIRNet

Image Super-Resolution using an Efficient Sub-Pixel CNN

Enhanced Deep Residual Networks for single-image super-resolution

Zero-DCE for low-light image enhancement

Data augmentation

CutMix data augmentation for image classification

MixUp augmentation for image classification

RandAugment for Image Classification for Improved Robustness

Image & Text

Image captioning

Natural language image search with a Dual Encoder

Vision models interpretability

Visualizing what convnets learn

Model interpretability with Integrated Gradients

Investigating Vision Transformer representations

Grad-CAM class activation visualization

Image similarity search

Near-duplicate image search

Semantic Image Clustering

Image similarity estimation using a Siamese Network with a contrastive loss

Image similarity estimation using a Siamese Network with a triplet loss

Metric learning for image similarity search

Metric learning for image similarity search using TensorFlow Similarity

Video

Video Classification with a CNN-RNN Architecture

Next-Frame Video Prediction with Convolutional LSTMs

Video Classification with Transformers

Video Vision Transformer

Other

Semi-supervision and domain adaptation with AdaMatch

Barlow Twins for Contrastive SSL

Class Attention Image Transformers with LayerScale

Consistency training with supervision

Distilling Vision Transformers

FixRes: Fixing train-test resolution discrepancy

Focal Modulation: A replacement for Self-Attention

Using the Forward-Forward Algorithm for Image Classification

Gradient Centralization for Better Training Performance

Knowledge Distillation

Learning to Resize in Computer Vision

Masked image modeling with Autoencoders

Self-supervised contrastive learning with NNCLR

Augmenting convnets with aggregated attention

Point cloud segmentation with PointNet

Semantic segmentation with SegFormer and Hugging Face Transformers

Self-supervised contrastive learning with SimSiam

Supervised Contrastive Learning

When Recurrence meets Transformers

Learning to tokenize in Vision Transformers

---

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

Machine translation

★

English-to-Spanish translation with KerasNLP

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 BERT

Language modeling

End-to-end Masked Language Modeling with BERT

Pretraining BERT with Hugging Face Transformers

Other

Training a language model from scratch with 🤗 Transformers and TPUs

Question Answering with Hugging Face Transformers

Abstractive Summarization with Hugging Face Transformers

---

Structured Data

Structured data classification

★

Structured data classification with FeatureSpace

★

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

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 KerasNLP

GPT text generation from scratch with KerasNLP

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

Density estimation using Real NVP

---

Audio Data

Automatic Speech Recognition using CTC

MelGAN-based spectrogram inversion using feature matching

Speaker Recognition

Automatic Speech Recognition with Transformer

English speaker accent recognition using Transfer Learning

Audio Classification with Hugging Face Transformers

---

Reinforcement Learning

Actor Critic Method

Deep Deterministic Policy Gradient (DDPG)

Deep Q-Learning for Atari Breakout

Proximal Policy Optimization

---

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

Simple custom layer example: Antirectifier

Probabilistic Bayesian Neural Networks

Knowledge distillation recipes

Creating TFRecords

Keras debugging tips

Endpoint layer pattern

Memory-efficient embeddings for recommendation systems

A Quasi-SVM in Keras

Estimating required sample size for model training

Evaluating and exporting scikit-learn metrics in a Keras callback

Customizing the convolution operation of a Conv2D layer

Writing Keras Models With TensorFlow NumPy

Serving TensorFlow models with TFServing

How to train a Keras model on TFRecord files

Trainer pattern

---

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 / TensorFlow 2 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.