hannw / Nlstm
Licence: mit
Nested LSTM Cell
Stars: ✭ 246
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Nlstm
Natural Language Processing With Tensorflow
Natural Language Processing with TensorFlow, published by Packt
Stars: ✭ 222 (-9.76%)
Mutual labels: lstm, rnn
Eeg Dl
A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.
Stars: ✭ 165 (-32.93%)
Mutual labels: lstm, rnn
Pytorch Kaldi
pytorch-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.
Stars: ✭ 2,097 (+752.44%)
Mutual labels: lstm, rnn
Chameleon recsys
Source code of CHAMELEON - A Deep Learning Meta-Architecture for News Recommender Systems
Stars: ✭ 202 (-17.89%)
Mutual labels: lstm, rnn
Crnn Audio Classification
UrbanSound classification using Convolutional Recurrent Networks in PyTorch
Stars: ✭ 235 (-4.47%)
Mutual labels: lstm, rnn
Lightnet
Efficient, transparent deep learning in hundreds of lines of code.
Stars: ✭ 243 (-1.22%)
Mutual labels: lstm, rnn
Rnn ctc
Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example.
Stars: ✭ 220 (-10.57%)
Mutual labels: lstm, rnn
Char Rnn Chinese
Multi-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.
Stars: ✭ 192 (-21.95%)
Mutual labels: lstm, rnn
Lstm Music Genre Classification
Music genre classification with LSTM Recurrent Neural Nets in Keras & PyTorch
Stars: ✭ 166 (-32.52%)
Mutual labels: lstm, rnn
Kprn
Reasoning Over Knowledge Graph Paths for Recommendation
Stars: ✭ 220 (-10.57%)
Mutual labels: lstm, rnn
Rnnvis
A visualization tool for understanding and debugging RNNs
Stars: ✭ 162 (-34.15%)
Mutual labels: lstm, rnn
Sign Language Gesture Recognition
Sign Language Gesture Recognition From Video Sequences Using RNN And CNN
Stars: ✭ 214 (-13.01%)
Mutual labels: lstm, rnn
Load forecasting
Load forcasting on Delhi area electric power load using ARIMA, RNN, LSTM and GRU models
Stars: ✭ 160 (-34.96%)
Mutual labels: lstm, rnn
Rnn For Joint Nlu
Pytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling" (https://arxiv.org/abs/1609.01454)
Stars: ✭ 176 (-28.46%)
Mutual labels: lstm, rnn
Pytorch Image Comp Rnn
PyTorch implementation of Full Resolution Image Compression with Recurrent Neural Networks
Stars: ✭ 146 (-40.65%)
Mutual labels: lstm, rnn
Tensorflow Bitcoin Robot
A Bitcoin trade robot based on Tensorflow LSTM model.Just for fun.
Stars: ✭ 155 (-36.99%)
Mutual labels: lstm, rnn
Stylenet
A cute multi-layer LSTM that can perform like a human 🎶
Stars: ✭ 187 (-23.98%)
Mutual labels: lstm, rnn
Pytorch Sentiment Analysis
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+1204.47%)
Mutual labels: lstm, rnn
nlstm
Tensorflow Implementation of Nested LSTM Cell
Here is a tensorflow implementation of Nested LSTM cell.
 |
|---|
| Nested LSTM Architecture. Courtesy of Moniz et al. |
NLSTM cell is basically a LSTM-like cell that uses the cell memory to control the state of the inner LSTM, and as such, the architecture can be generalized to multiple layers. For a comparison between LSTM and NLSTM,
 |
|---|
| LSTM and stacked LSTM, versus nested LSTM. Courtesy of Moniz et al. |
The implementation here is compatible with the tensorflow rnn API.
from rnn_cell import NLSTMCell
cell = NLSTMCell(num_units=3, depth=2)
init_state = cell.zero_state(batch_size, dtype=tf.float32)
output, new_state = cell(inputs, state=init_state)
...
Ref:
- Moniz et al, "Nested LSTMs." https://arxiv.org/abs/1801.10308
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].