Deep Learning

Description

Deep Learning frameworks provide support for training and inference of deep neural networks (more than 3 layers). Deep Learning is compute intensive, and most Deep Learning focused frameworks support GPU acceleration.

Projects

17

Lines Committed vs. Age Chart (click to view)

Lines Committed vs. Age Chart (click to view)

Projects

Project

Size Score

Trend Score

Byline

Caffe

4.5

1.75

Lightweight Deep Learning Framework

Caffe2

3.25

1.75

Lightweight Deep Learning Framework

Chainer

6.75

1.5

A flexible framework of neural networks for deep learning

CNTK

6.0

1.75

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

DeepForge

4.5

5.0

A modern development environment for deep learning

DeepLearning4j

6.75

5.75

Eclipse Deeplearning4j, ND4J, DataVec and more - deep learning & linear algebra for Java/Scala with GPUs + Spark

fastai

7.75

4.75

The fastai deep learning library, plus lessons and tutorials

framework

4.5

2.25

Machine learning, computer vision, statistics and general scientific computing for .NET

Keras

7.0

6.0

Deep Learning for humans

MXNet

7.75

3.25

A flexible and efficient library for deep learning.

neurojs

1.0

3.0

A JavaScript deep learning and reinforcement learning library.

nnabla

5.25

7.0

Neural Network Libraries is a deep learning framework that is intended to be used for research, development and production.

PyTorch

8.75

7.75

Tensors and Dynamic neural networks in Python with strong GPU acceleration.

TensorFlow

10.0

5.5

An open source machine learning framework for everyone.

TensorFlow.js

7.25

5.5

A WebGL accelerated JavaScript library for training and deploying ML models.

Theano

5.5

2.25

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently.

TVM

5.25

8.25

Open deep learning compiler stack for cpu, gpu and specialized accelerators