Table of Content

Playground

  1. Tensorflow Playground: Great tool to understand how all the pieces in a modern Deep Learning model training pipeline (like the one Keras enables) come together and to play with it on small datasets, all without writing any code.
  2. ConvNetJS served as one of the inspirations for Tensorflow Playground and has a few demos of its own.
  3. GAN Lab is just like Tensorflow Playground, but for GANs
  4. AI Experiments is a showcase of simple and fun applications of Machine Learning and Deep Learning. If you are looking for an idea for your next project, this could help.
  5. TensorFire has some great demos.
  6. For Neural Style Transfer, Deepart has a demo where you can create your own images and a gallery page where you can see what others have created.
  7. Magenta is great for making Music and Art with Tensorflow. It has a demo page

Modeling Tools/Utilities

  1. https://github.com/joeddav/devol
  2. https://github.com/maxpumperla/hyperas
  3. https://github.com/keras-team/keras-contrib
  4. Accelerating Deep Learning with Multiprocess Image Augmentation in Keras (accompanying blog post)
  5. ml-tools: Tools for common machine learning tasks using Tensorflow and Keras
  6. https://github.com/kuza55/keras-extras
  7. keras-multi-gpu: Multi-GPU data-parallel training in Keras
  8. keras_callbacks_example: Keras Callback Examples

Implementations (from Scratch)/Pre-trained Models

  1. https://github.com/raghakot/keras-resnet
  2. https://github.com/XifengGuo/CapsNet-Keras Tags:
  3. https://github.com/kentsommer/keras-inceptionV4
  4. https://github.com/fchollet/deep-learning-models
  5. https://github.com/titu1994/DenseNet
  6. BatchRenormalization: Batch Renormalization algorithm implementation in Keras
  7. mlp: Multilayer Perceptron Keras wrapper for sklearn
  8. Image-Classification-Mobile: Sandbox for training large-scale image classification networks for embedded systems, including collection of pretrained classification models for Keras with MXNet backend
  9. Keras Implementation of Ladder Network for Semi-Supervised Learning

Visualization Tools

  1. https://github.com/merantix/picasso
  2. https://github.com/raghakot/keras-vis
  3. https://github.com/fchollet/hualos
  4. quiver: Interactive convnet features visualization for Keras (homepage)
  5. hera: Train/evaluate a Keras model, get metrics streamed to a dashboard in your browser
  6. picard: Easily declare large spaces of (keras) neural networks and run (hyperopt) optimization experiments on them (homepage)
  7. keras-visualize-activations: Activation Maps Visualization for Keras

Learning

Beginner Resources

  1. http://neuralnetworksanddeeplearning.com/index.html (great for those just starting with Deep Learning)

Curated Resources

  1. https://github.com/sachinruk/deepschool.io
  2. https://github.com/leriomaggio/deep-learning-keras-tensorflow
  3. https://github.com/kailashahirwar/cheatsheets-ai
  4. https://github.com/donnemartin/data-science-ipython-notebooks
  5. https://github.com/xingkongliang/Keras-Tutorials
  6. https://github.com/anujgupta82/DeepNets/tree/master/Keras/Keras_from_scratch
  7. https://github.com/chibuk/simple-cnn-keras-colaboratory

Art

  1. https://github.com/OsciiArt/DeepAA
  2. https://github.com/titu1994/Neural-Style-Transfer

Interoperating with other frameworks

  1. https://github.com/Microsoft/MMdnn
  2. model-converters: Tools for converting Keras models for use with other ML frameworks
  3. PyTorch to Keras model converter
  4. Gluon to Keras model converter

Recurrent Networks

  1. recurrentshop: Framework for building complex recurrent neural networks with Keras

Deployment

  1. https://sahnimanas.github.io/2018/06/24/quantization-in-tf-lite.html

Segmentation

  1. https://github.com/mrgloom/awesome-semantic-segmentation

Data Tools

  1. https://github.com/wkentaro/labelme

Misc

  1. https://medium.com/@ageitgey/the-dumb-reason-your-fancy-computer-vision-app-isnt-working-exif-orientation-73166c7d39da
  2. https://timdettmers.com/2019/04/03/which-gpu-for-deep-learning/
  3. https://medium.com/@hadyelsahar/how-do-you-manage-your-machine-learning-experiments-ab87508348ac