Skip to content

A curated list of awesome Keras projects, libraries and resources

License

Notifications You must be signed in to change notification settings

markusschanta/awesome-keras

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Awesome Keras Awesome Hits

A curated list of awesome Keras projects, libraries and resources. 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.


Awesome Keras logo

🎉 This project is brand new: Your 🤝 contributions 🤝 and ⭐️ stars ⭐️ are much appreciated! 🎉

Contents


Core Libraries

  • keras - Deep learning for humans.
  • autokeras - AutoML library for deep learning.
  • keras-tuner - Hyperparameter tuning for humans.
  • keras-cv - Industry-strength Computer Vision workflows with Keras.
  • keras-nlp - Development environment with seamless data transmission from one language to another.

Frameworks

  • byteps - A high performance and generic framework for distributed DNN training.
  • deep-learning-model-convertor - An overview of packages for model conversion between frameworks.
  • deepo - A collection of/framework to create deep learning Docker images.
  • einops - A library for flexible and powerful tensor operations to make code more readable and reliable.
  • horovod - A distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
  • hyperas - Keras + Hyperopt: A simple wrapper for hyperparameter optimization.
  • keras-rl - Deep reinforcement learning for Keras.
  • MMdnn - A cross-framework tool to convert, visualize and diagnose deep learning models.
  • ncnn - A high-performance neural network framework optimized for mobile platforms.
  • onnx - An open standard for machine learning interoperability.
  • wandb - A tool for visualizing and tracking your machine learning experiments.

Network Visualisation

  • keras-sequential-ascii - An ASCII summary for simple sequential models in Keras.
  • keras-vis - A neural network visualization toolkit for keras.
  • netron - A visualizer for neural network, deep learning and machine learning models.
  • tensorspace - A 3D visualization framework for neural networks.
  • TtDoVAoNN - A list of tools to design or visualize architecture of neural networks.
  • visualkeras - A Python package to help visualize Keras neural network architectures.

Examples/Notebooks

  • ASRT_SpeechRecognition - A deep learning-Based Chinese speech recognition system.
  • D2L.ai - An interactive deep learning book with multi-framework code, math, and discussions.
  • data-science-ipython-notebooks - A collection of data science notebooks (dedicated Keras section).
  • deepjazz - Deep learning-driven jazz music generation using Keras and Theano.
  • donkeycar - Open source hardware and software platform to build a small scale self driving car.
  • image-super-resolution - A implementation to scale images using residual dense and adversarial networks.
  • imgclsmob - A sandbox for training convolutional neuronal networks.
  • keras-attention-mechanism - A many-to-one attention mechanism implementation in Keras.
  • Keras-GAN - A Keras implementation of Generative Adversarial Networks.
  • Mask_RCNN - An implementation of Mask R-CNN for object detection and segmentation on Keras and TensorFlow.
  • satellite-image-deep-learning - A collection of resources relating to deep learning with satellite & aerial imagery.
  • Screenshot-to-code - A neural network that transforms a design mock-up into a static website.
  • sketch-code - A Keras model to generate HTML code from hand-drawn website mockups.
  • spektral - Graph Neural Networks with Keras and Tensorflow.
  • textgenrnn - A library that allows simple training of text-generating neural networks with a few lines of code.
  • unet - An implementation of U-Net using Keras.

Documentation

Community Resources