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.

Run keras models with a Flux backend

Collection of Keras models used for classification

Implementing Deep learning in R using Keras and Tensorflow packages for R and implementing a Multi layer perceptron Model on MNIST dataset and doing Digit Recognition

深度学习相关代码

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

Transfer pre-trained VRN model from torch to Keras/Tensorflow

PyTorch to Keras model convertor

Extending Keras to support tfrecord dataset

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".

A tutorial exploring multiple approaches to deploy a trained TensorFlow (or Keras) model or multiple models for prediction.

PyTorch to Keras model convertor

Serving a keras model (neural networks) in a website with the python Django-REST framework.

Example of Multiple Multivariate Time Series Prediction with LSTM Recurrent Neural Networks in Python with Keras.

UNet for Multiclass Semantic Segmentation, on Keras, based on Segmentation Models' Unet libray

Deep Learning using Rectified Linear Units (ReLU)

DeepStack: Ensembling Keras Deep Learning Models into the next Performance Level

Train a state-of-the-art yolov3 object detector from scratch!

Keras implementation of a ResNet-CAM model