DeepjazzDeep learning driven jazz generation using Keras & Theano!
Har Stacked Residual Bidir LstmsUsing deep stacked residual bidirectional LSTM cells (RNN) with TensorFlow, we do Human Activity Recognition (HAR). Classifying the type of movement amongst 6 categories or 18 categories on 2 different datasets.
Crnn PytorchPytorch implementation of CRNN (CNN + RNN + CTCLoss) for all language OCR.
Pytorch Seq2seqTutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
LightnetEfficient, transparent deep learning in hundreds of lines of code.
Caption generatorA modular library built on top of Keras and TensorFlow to generate a caption in natural language for any input image.
Rnn ctcRecurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.
KprnReasoning Over Knowledge Graph Paths for Recommendation
HasteHaste: a fast, simple, and open RNN library
ShakkalaDeep learning for Arabic text Vocalization - التشكيل الالي للنصوص العربية
Doc Han AttHierarchical Attention Networks for Chinese Sentiment Classification
Chameleon recsysSource code of CHAMELEON - A Deep Learning Meta-Architecture for News Recommender Systems
IseebetteriSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
Char Rnn ChineseMulti-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch. Based on code of https://github.com/karpathy/char-rnn. Support Chinese and other things.
StylenetA cute multi-layer LSTM that can perform like a human 🎶
Rnn For Joint NluPytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling" (https://arxiv.org/abs/1609.01454)
Eeg DlA Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.
Pytorch Kaldipytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
RnnvisA visualization tool for understanding and debugging RNNs
Load forecastingLoad forcasting on Delhi area electric power load using ARIMA, RNN, LSTM and GRU models
AudioowlFast and simple music and audio analysis using RNN in Python 🕵️♀️ 🥁
HartHierarchical Attentive Recurrent Tracking
RnnoiseRecurrent neural network for audio noise reduction
Pytorch Image Comp RnnPyTorch implementation of Full Resolution Image Compression with Recurrent Neural Networks
Vae SeqVariational Auto-Encoders in a Sequential Setting.
QrnQuery-Reduction Networks (QRN)
Rnn recsysOur implementation of the paper "Embedding-based News Recommendation for Millions of Users"
Chinese Chatbot中文聊天机器人,基于10万组对白训练而成,采用注意力机制,对一般问题都会生成一个有意义的答复。已上传模型,可直接运行,跑不起来直播吃键盘。
Midi RnnGenerate monophonic melodies with machine learning using a basic LSTM RNN
Linear Attention Recurrent Neural NetworkA recurrent attention module consisting of an LSTM cell which can query its own past cell states by the means of windowed multi-head attention. The formulas are derived from the BN-LSTM and the Transformer Network. The LARNN cell with attention can be easily used inside a loop on the cell state, just like any other RNN. (LARNN)