mohit1997 / Deepzip
Licence: mit
NN based lossless compression
Stars: ✭ 69
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Deepzip
Deep Music Genre Classification
🎵 Using Deep Learning to Categorize Music as Time Progresses Through Spectrogram Analysis
Stars: ✭ 23 (-66.67%)
Mutual labels: cnn, lstm
Neural Image Captioning
Implementation of Neural Image Captioning model using Keras with Theano backend
Stars: ✭ 12 (-82.61%)
Mutual labels: cnn, lstm
Tensorflow Lstm Sin
TensorFlow 1.3 experiment with LSTM (and GRU) RNNs for sine prediction
Stars: ✭ 52 (-24.64%)
Mutual labels: lstm, prediction
Deep Learning Time Series
List of papers, code and experiments using deep learning for time series forecasting
Stars: ✭ 796 (+1053.62%)
Mutual labels: lstm, prediction
Rnn Theano
使用Theano实现的一些RNN代码，包括最基本的RNN，LSTM，以及部分Attention模型，如论文MLSTM等
Stars: ✭ 31 (-55.07%)
Mutual labels: cnn, lstm
Textclassificationbenchmark
A Benchmark of Text Classification in PyTorch
Stars: ✭ 534 (+673.91%)
Mutual labels: cnn, lstm
Deepseqslam
The Official Deep Learning Framework for Route-based Place Recognition
Stars: ✭ 49 (-28.99%)
Mutual labels: cnn, lstm
Text Classification
Implementation of papers for text classification task on DBpedia
Stars: ✭ 682 (+888.41%)
Mutual labels: cnn, lstm
Multi Class Text Classification Cnn Rnn
Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.
Stars: ✭ 570 (+726.09%)
Mutual labels: cnn, lstm
Tensorflow Tutorial
Some interesting TensorFlow tutorials for beginners.
Stars: ✭ 893 (+1194.2%)
Mutual labels: cnn, lstm
Video Classification
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Stars: ✭ 543 (+686.96%)
Mutual labels: cnn, lstm
Qa Rankit
QA - Answer Selection (Rank candidate answers for a given question)
Stars: ✭ 30 (-56.52%)
Mutual labels: cnn, lstm
Cryptocurrencyprediction
Predict Cryptocurrency Price with Deep Learning
Stars: ✭ 453 (+556.52%)
Mutual labels: cnn, lstm
Lstm Fcn
Codebase for the paper LSTM Fully Convolutional Networks for Time Series Classification
Stars: ✭ 482 (+598.55%)
Mutual labels: cnn, lstm
Twitter Sentiment Analysis
Sentiment analysis on tweets using Naive Bayes, SVM, CNN, LSTM, etc.
Stars: ✭ 978 (+1317.39%)
Mutual labels: cnn, lstm
Lstm Context Embeddings
Augmenting word embeddings with their surrounding context using bidirectional RNN
Stars: ✭ 57 (-17.39%)
Mutual labels: cnn, lstm
DeepZip
Description
Data compression using neural networks
DeepZip: Lossless Data Compression using Recurrent Neural Networks
Requirements
- GPU, nvidia-docker (or try alternative installation)
- python 2/3
- numpy
- sklearn
- keras 2.2.2
- tensorflow (cpu/gpu) 1.8
(nvidia-docker is currently required to run the code) A simple way to install and run is to use the docker files provided:
cd docker
make bash BACKEND=tensorflow GPU=0 DATA=/path/to/data/
Alternative Installation
cd DeepZip
python3 -m venv tf
source tf/bin/activate
bash install.sh
Code
To run a compression experiment:
Data Preparation
- Place all the data to be compressed in data/files_to_be_compressed
- Run the parser
cd data
./run_parser.sh
Running models
- All the models are listed in models.py
- Pick a model, to run compression experiment on all the data files in the data/files_to_be_compressed directory
cd src
./run_experiments.sh biLSTM GPUID
Note: GPUID by default can be set to 0. The corresponding command would be then ./run_experiments.sh biLSTM 0
Please cite if you utilize the code in this repository.
@inproceedings{7fcb664b03ac4d6497048954d756b91f,
title = "DeepZip: Lossless Data Compression Using Recurrent Neural Networks",
author = "Mohit Goyal and Kedar Tatwawadi and Shubham Chandak and Idoia Ochoa",
year = "2019",
month = "5",
day = "10",
doi = "10.1109/DCC.2019.00087",
language = "English (US)",
series = "Data Compression Conference Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
editor = "Ali Bilgin and Storer, {James A.} and Marcellin, {Michael W.} and Joan Serra-Sagrista",
booktitle = "Proceedings - DCC 2019",
address = "United States",
}
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].