Deep Learning Frameworks 2019 | Which Deep Learning Framework To Use | Deep Learning | Simplilearn

How Big Data evolved?
Deep Learning
Frameworks

Microsoft CNTKTensorFlow

TensorFlow
Developed by
Google Brain Team

TensorFlow
Developed by
Google Brain Team
Supports languages

TensorFlow
Developed by
Google Brain Team
Supports languages Uses dataflow graphs to
process data

TensorFlow
Developed by
Google Brain Team
process data
Easy to build Machine
Learning models

TensorFlow
Developed by
Google Brain Team
process data
Learning models
Robust Machine Learning
production

TensorFlow
Developed by
Google Brain Team
process data
Learning models
Powerful experimentation for
research
production

TensorFlow
Developed by
Google Brain Team
process data
TensorBoard for data
visualization
Learning models
Powerful experimentation for
research
production

Microsoft CNTKKeras

Keras
Francois Chollet is the author of
keras, with over 350,000 users
and 700+ open-source
contributors

Keras
High-level neural network API,
written in Python
contributors

Keras
Runs on top of TF,
Theano, CNTK
CNTK
contributors
written in Python

Keras
CNTK
Used in several startups,
research labs, and companies
written in Python
Runs on top of TF,
Theano, CNTK
contributors

Keras
CNTK
Used in several startups,
research labs, and companies
User-friendly as it offers simple APIs and provides clear
and actionable feedback upon user error
Provides modularity as a sequence or a graph of standalone,
fully configurable modules that can be plugged together with
as few restrictions as possible
Easily extensible as new modules are simple to add. This feature
makes Keras suitable for advanced research
1
2
3
Runs on top of TF,
Theano, CNTK
contributors
written in Python

Microsoft CNTKPyTorch

PyTorch
Authored by Adam Paszke, Sam Gross, Soumith
Chintala and Gregory Chanan

PyTorch
Lua based scientific computing framework for Machine
Learning and Deep Learning algorithms

PyTorch
It employed CUDA along with C/C++ libraries for
processing and was designed to scale the
production of building models and overall flexibility

PyTorch
Widely used in companies like

PyTorch
Widely used in companies like
Provides flexibility and speed due to its hybrid front-end
Enables scalable distributed training and performance
optimization in research and production using
torch.distributed backend
Deep integration into Python allows popular libraries and
packages to be used for quickly writing neural network
layers in Python.
1
2
3

Microsoft CNTKTheano

Theano
Developed by Written in

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

Theano
Python library that allows to define, optimize, and
evaluate mathematical expressions involving multi-
dimensional arrays efficiently
• Theano has tight integration with NumPy for data computations
• Uses GPU’s to perform data-intensive computations which are much
faster than on a CPU
• Has extensive unit-testing and self-verification that can detect and
diagnose many types of errors

Microsoft CNTKDeep Learning 4 Java

Deep Learning 4 Java
Developed by a Machine Learning
group led by Adam Gibson

Written in Java and Scala, DL4J supports different neural
networks like CNN, RNN, and LSTM

DL4J was contributed to Eclipse Foundation.
Integrated with Hadoop and Apache Spark, DL4J
brings AI to business environments for use on
distributed CPUs and GPUs

DL4J was contributed to Eclipse Foundation.
Integrated with Hadoop and Apache Spark, DL4J
brings AI to business environments for use on
distributed CPUs and GPUs
• Provides a distributed computing framework as training
with DL4J occurs in a cluster
• Includes an n-dimensional array class using ND4J that
allows scientific computing in Java and Scala
• Offers a vector space modeling and topic modeling
toolkit that is designed to handle large text sets and
perform NLP

Microsoft CNTKCaffe

Caffe
Caffe stands for Convolutional Architecture for Fast Feature EmbeddingDeveloped at

Caffe
Caffe stands for Convolutional Architecture for Fast Feature Embedding
Written in C++, with a Python interface
Developed at

Caffe
Generally used for image detection and
classification
Developed at

Caffe
Generally used for image detection and
classification
• Used in academic research projects, startup
prototypes, and large-scale industrial applications in
vision, speech, and multimedia
• Caffe supports GPU and CPU-based acceleration
computational kernel libraries such as NVIDIA, cuDNN
and, IntelMLK
• Offers high speed can process over 60M images per
day with a single NVIDIA K40 GPU
Developed at

Microsoft CNTKChainer

Chainer
Preferred Networks in collaboration with
IBM, Intel, Microsoft, and Nvidia
Developed by

Chainer
Written purely in Python, it runs on top of
Numpy and CuPy Python libraries
Developed by

Chainer
Provides a number of extended libraries
Developed by

Chainer
Developed by
Provides a number of extended libraries • Supports CUDA computation. It only requires a few
lines of code to leverage a GPU. It also runs on
multiple GPUs with little effort
• Provides various network architectures, including
feed-forward nets, convnets, recurrent nets, and
recursive nets

Microsoft CNTKMicrosoft CNTK

Microsoft Cognitive Toolkit
CNTK
Developed by

CNTK
CNTK is a Deep Learning framework that builds a neural network as a
series of computational steps via a directed graph
Developed by

CNTK
Supports interfaces such as Python, C++
Developed by

CNTK
Used mainly for
Developed by

CNTK
Developed by
Used mainly for
• Designed for speed and efficiency, CNTK scales well in
production using GPUs but has limited support from the
community
• Supports both RNN and CNN type of neural models
capable of handling image, handwriting and speech
recognition problems

Deep Learning Frameworks 2019 | Which Deep Learning Framework To Use | Deep Learning | Simplilearn

Deep Learning Frameworks 2019 | Which Deep Learning Framework To Use | Deep Learning | Simplilearn

In this document

More Related Content

What's hot

Similar to Deep Learning Frameworks 2019 | Which Deep Learning Framework To Use | Deep Learning | Simplilearn

More from Simplilearn

Recently uploaded