Popularity

5.0

Declining

Activity

0.0

Stable

Stars 1,170

Watchers 82

Forks 127

Last Commit almost 3 years ago

Description

GPU-Accelerated Deep Learning Library in Python

Hebel is a library for deep learning with neural networks in Python using GPU acceleration with CUDA through PyCUDA. It implements the most important types of neural network models and offers a variety of different activation functions and training methods such as momentum, Nesterov momentum, dropout, and early stopping.

I no longer actively develop Hebel. If you are looking for a deep learning framework in Python, I now recommend Chainer.

Code Quality Rank: L2

Programming language: Python

License: GNU General Public License v3.0 only

Tags: Machine Learning Scientific Engineering Image Recognition Artificial Intelligence

Latest version: v0.02.1

hebel alternatives and similar packages

Based on the "Machine Learning" category.
Alternatively, view hebel alternatives based on common mentions on social networks and blogs.

tensorflow

10.0 10.0 L1 hebel VS tensorflow

An Open Source Machine Learning Framework for Everyone
scikit-learn

9.9 9.8 L3 hebel VS scikit-learn

scikit-learn: machine learning in Python

Write Clean Python Code. Always.

Sonar helps you commit clean code every time. With over 225 unique rules to find Python bugs, code smells & vulnerabilities, Sonar finds the issues while you focus on the work.

Promo www.sonarsource.com

Keras

9.9 9.6 L2 hebel VS Keras

Deep Learning for humans
xgboost

9.8 9.5 L1 hebel VS xgboost

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
gym

9.8 5.2 hebel VS gym

A toolkit for developing and comparing reinforcement learning algorithms.
CNTK

9.6 0.0 L1 hebel VS CNTK

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
PaddlePaddle

9.6 9.9 L1 hebel VS PaddlePaddle

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
Prophet

9.5 6.5 hebel VS Prophet

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
gensim

9.5 8.0 L3 hebel VS gensim

Topic Modelling for Humans
MLflow

9.5 9.8 hebel VS MLflow

Open source platform for the machine learning lifecycle
MindsDB

9.5 10.0 hebel VS MindsDB

MindsDB connects AI models to databases.
TFLearn

9.2 0.0 L3 hebel VS TFLearn

Deep learning library featuring a higher-level API for TensorFlow.
NuPIC

8.8 0.0 L3 hebel VS NuPIC

Numenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strictly on the neuroscience of the neocortex.
H2O

8.8 9.5 hebel VS H2O

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
Pyro.ai

8.7 7.8 hebel VS Pyro.ai

Deep universal probabilistic programming with Python and PyTorch
Surprise

8.4 3.2 L4 hebel VS Surprise

A Python scikit for building and analyzing recommender systems
srez

8.3 0.0 L5 hebel VS srez

Image super-resolution through deep learning
LightFM

7.9 6.8 L4 hebel VS LightFM

A Python implementation of LightFM, a hybrid recommendation algorithm.
Pylearn2

7.9 0.0 L2 hebel VS Pylearn2

Warning: This project does not have any current developer. See bellow.
PyBrain

7.7 0.0 L4 hebel VS PyBrain

Another Python Machine Learning Library.
Sacred

7.6 6.4 hebel VS Sacred

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
skflow

7.6 1.3 L4 hebel VS skflow

Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning
Clairvoyant

7.2 0.0 L3 hebel VS Clairvoyant

Software designed to identify and monitor social/historical cues for short term stock movement
Metrics

6.2 0.0 hebel VS Metrics

Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB / Octave
python-recsys

6.2 0.0 L4 hebel VS python-recsys

A python library for implementing a recommender system
karateclub

6.1 6.0 hebel VS karateclub

Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)
awesome-embedding-models

6.0 0.0 hebel VS awesome-embedding-models

A curated list of awesome embedding models tutorials, projects and communities.
pydeep

6.0 0.0 L3 hebel VS pydeep

Deep learning in Python
Crab

5.7 0.0 L2 hebel VS Crab

Crab is a ﬂexible, fast recommender engine for Python that integrates classic information ﬁltering recommendation algorithms in the world of scientiﬁc Python packages (numpy, scipy, matplotlib).
adaptive

4.5 8.1 hebel VS adaptive

:chart_with_upwards_trend: Adaptive: parallel active learning of mathematical functions
seqeval

4.5 0.0 hebel VS seqeval

A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)
Xorbits

4.2 8.8 hebel VS Xorbits

Scalable Python DS & ML, in an API compatible & lightning fast way.
TrueSkill, the video game rating system

4.2 0.0 hebel VS TrueSkill, the video game rating system

An implementation of the TrueSkill rating system for Python
rwa

3.9 0.0 L5 hebel VS rwa

Machine Learning on Sequential Data Using a Recurrent Weighted Average
pdpipe

3.9 0.0 hebel VS pdpipe

Easy pipelines for pandas DataFrames.
SciKit-Learn Laboratory

3.8 0.0 hebel VS SciKit-Learn Laboratory

SciKit-Learn Laboratory (SKLL) makes it easy to run machine learning experiments.
Feature Forge

3.5 0.0 L4 hebel VS Feature Forge

A set of tools for creating and testing machine learning features, with a scikit-learn compatible API
Data Flow Facilitator for Machine Learning (dffml)

3.3 8.3 hebel VS Data Flow Facilitator for Machine Learning (dffml)

The easiest way to use Machine Learning. Mix and match underlying ML libraries and data set sources. Generate new datasets or modify existing ones with ease.
nptyping

3.2 0.0 hebel VS nptyping

💡 Type hints for Numpy and Pandas
brew

3.2 0.0 L4 hebel VS brew

Multiple Classifier Systems and Ensemble Learning Library in Python.
bodywork

3.1 0.0 hebel VS bodywork

ML pipeline orchestration and model deployments on Kubernetes, made really easy.
MLP Classifier

2.8 0.0 L4 hebel VS MLP Classifier

A handwritten multilayer perceptron classifer using numpy.
redframes

2.7 10.0 hebel VS redframes

General Purpose Data Manipulation Library
OptaPy

2.7 0.0 hebel VS OptaPy

OptaPy is an AI constraint solver for Python to optimize planning and scheduling problems.
vowpal_porpoise

2.5 0.0 L3 hebel VS vowpal_porpoise

lightweight python wrapper for vowpal wabbit
openskill.py

2.4 0.0 hebel VS openskill.py

Multiplayer Rating System. No Friction.
omega-ml

1.8 5.8 hebel VS omega-ml

MLOps simplified. From ML Pipeline ⇨ Data Product without the hassle
ChaiPy

1.5 0.0 hebel VS ChaiPy

A developer interface for creating advanced chatbots for the Chai app.
neptune-contrib

1.4 0.0 hebel VS neptune-contrib

This library is a location of the LegacyLogger for PyTorch Lightning.
tfgraphviz

1.4 0.0 L5 hebel VS tfgraphviz

A visualization tool to show a TensorFlow's graph like TensorBoard

* Code Quality Rankings and insights are calculated and provided by Lumnify.
They vary from L1 to L5 with "L5" being the highest.

Do you think we are missing an alternative of hebel or a related project?

Add another 'Machine Learning' Package

Popular Comparisons

README

Hebel

GPU-Accelerated Deep Learning Library in Python

Hebel is a library for deep learning with neural networks in Python using GPU acceleration with CUDA through PyCUDA. It implements the most important types of neural network models and offers a variety of different activation functions and training methods such as momentum, Nesterov momentum, dropout, and early stopping.

I no longer actively develop Hebel. If you are looking for a deep learning framework in Python, I now recommend Chainer.

Models

Right now, Hebel implements feed-forward neural networks for classification and regression on one or multiple tasks. Other models such as Autoencoder, Convolutional neural nets, and Restricted Boltzman machines are planned for the future.

Hebel implements dropout as well as L1 and L2 weight decay for regularization.

Optimization

Hebel implements stochastic gradient descent (SGD) with regular and Nesterov momentum.

Compatibility

Currently, Hebel will run on Linux and Windows, and probably Mac OS X (not tested).

Dependencies

PyCUDA
numpy
PyYAML
skdata (only for MNIST example)

Installation

Hebel is on PyPi, so you can install it with

pip install hebel

Getting started

Study the yaml configuration files in examples/ and run

python train_model.py examples/mnist_neural_net_shallow.yml

The script will create a directory in examples/mnist where the models and logs are saved.

Read the Getting started guide at hebel.readthedocs.org/en/latest/getting_started.html for more information.

Documentation

hebel.readthedocs.org

Contact

Maintained by Hannes Bretschneider ([email protected]). If your are using Hebel, please let me know whether you find it useful and file a Github issue if you find any bugs or have feature requests.

Citing

If you make use of Hebel in your research, please cite it. The BibTeX reference is

@article{Bretschneider:10050,
  author        = "Hannes Bretschneider",
  title         = "{Hebel - GPU-Accelerated Deep Learning Library in Python}",
  month         = "May",
  year          = "2014",
  doi           = "10.5281/zenodo.10050",
  url           = "https://zenodo.org/record/10050",
}

What's with the name?

Hebel is the German word for lever, one of the oldest tools that humans use. As Archimedes said it: "Give me a lever long enough and a fulcrum on which to place it, and I shall move the world."