Displaying 1 to 14 from 14 results

babble-rnn - babble-rnn is a research project in the use of machine learning to generate new speech by modelling human speech audio, without any intermediate text or word representations

  •    Jupyter

babble-rnn is a research project in the use of machine learning to generate new speech by modelling human speech audio, without any intermediate text or word representations. The idea is to learn to speak through imitation, much like a baby might. The goal is to generate a babbling audio output that emulates the speech patterns of the original speaker, ideally incorporating real words into the output. The implementation is based on Keras / Theano, generating an LSTM RNN; and Codec 2, an open source speech audio compression algorithm. The resulting models have learned the most common audio sequences of a 'performer', and can generate a probable babbling audio sequence when provided a seed sequence.

Video2Language - Generating video descriptions using deep learning in Keras

  •    Python

You can fix it by upgrading Tensorflow. The video captioning model here uses Mean Pooled ResNet50 features of video frames along with Object, Action and Attribute tags predicted by a simple feedforward network.

open-solution-cdiscount-starter - Open solution to the Cdiscount’s Image Classification Challenge

  •    Python

This is ready to use, end-to-end sample solution for the currently running Kaggle Cdiscount challenge. It involves data loading and augmentation, model training (many different architectures), ensembling and submit generator.




GestureAI - RNN(Recurrent Nerural network) model which recognize hand-gestures drawing 5 figures.

  •    Jupyter

GestureAI is a RNN(Recurrent Nerural network) model which recognize hand-gestures drawing 5 figures(Circl, Rectangle, Triangle, Cross and the other). This dataset of hand-motion drawing 5 figures is sequences of 3-axis accelerations captured by iPhone. Example to implement RNN in Keras gets 90.8% accuracy by Cross-validation. You can use direct links to download the dataset.


ResNetCAM-keras - Keras implementation of a ResNet-CAM model

  •    Python

The original Matlab implementation and paper (for AlexNet, GoogLeNet, and VGG16) can be found here. A Keras implementation of VGG-CAM can be found here. This implementation is written in Keras and uses ResNet-50, which was not explored in the original paper.

Keras-Classification-Models - Collection of Keras models used for classification

  •    Python

A set of models which allow easy creation of Keras models to be used for classification purposes. Also contains modules which offer implementations of recent papers. An implementation of "SparseNets" from the paper Sparsely Connected Convolutional Networks in Keras 2.0+.

audio-pretrained-model - A collection of Audio and Speech pre-trained models.

  •    

A pre-trained model is a model created by some one else to solve a similar problem. Instead of building a model from scratch to solve a similar problem, we can use the model trained on other problem as a starting point. A pre-trained model may not be 100% accurate in your application. You can see visualizations of each model's network architecture by using Netron.

minos - Deep learning, architecture and hyper parameters search with genetic algorithms

  •    Python

Search for neural networks architecture & hyper parameters with genetic algorithms. It is built on top of Keras+Tensorflow to build/train/evaluate the models, and uses DEAP for the genetic algorithms. Then you define the parameters of the training. If you specify only the name of the optimizer to use, and no parameters, random parameters will be tested during the experiment, hopefully converging to optimal parameters. You can choose to stop the training after a fixed number of epochs, or when the accuracy of the model evaluated stops increasing.

keras-model-zoo - Ready to go, downloadable models for Keras

  •    

We will host the model file. Do a pull request with your updates and a link to your model. During review we will download and host your model on our S3 so you can update your pull request URL to one that we will host. You simply need to find a way to get your model in our hands temporarily and we'll take on the hosting for the repo. Update the README.md to have all the information on your provided model. Then add a folder in the /info section that includes credit, examples, and more friendly information on your trained keras model.






We have large collection of open source products. Follow the tags from Tag Cloud >>


Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.