SlideShare a Scribd company logo
1 of 18
Copyright © 2017, edureka and/or its affiliates. All rights reserved.
Copyright © 2017, edureka and/or its affiliates. All rights reserved.
Deep Learning Frameworks
Let’s look highlights from PyTorch and TensorFlow
Copyright © 2018, edureka and/or its affiliates. All rights reserved.
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Deep Learning Frameworks
Dynamic
Computation
Graphs
Python Support
Support
for CUDA
Easy to Use API
Fast and Feels
Native
Actively used
Visualizer
Easily Trainable
Layered
Components
Open Source
Flexible
Google
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
PyTorch v/s TensorFlow
An insight comparing both of the frameworks
Copyright © 2018, edureka and/or its affiliates. All rights reserved.
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Comparison Factors
Deployment5
Documentation6
Device Management7
Custom Extensions8
Ramp-Up Time 1
Graph Creation 2
Coverage 3
Serialization 4
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Ramp-Up Time
PyTorch
GPU enabled drop-in replacement
for NumPy
NumPy functionality makes it easier
to learn
TensorFlow
TensorFlow code gets compiled into a graph
by Python.
TensorFlow Execution Engine is used.
PyTorch
PyTorch code is known for executing
faster and more efficiently
Not many extra concepts to learn.
TensorFlow
Extra concepts needed such as
Session, Variable Scoping and
Placeholders.
More Boilerplate code needed
1
3
2
4
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Graph Construction and Debugging
PyTorch PyTorch
TensorFlow TensorFlow
Dynamic Computation Graphs
Graphs can be built at runtime
Graph construction is static
Graphs need to be compiled first
Debugging PyTorch is same as Python code
pdb – Python Debugger can be used
Learn TensorFlow debugger(tfdbg) – Extra!
Request variables from session to inspect
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Coverage
Less features compared to TensorFlow
Not as popular as TensorFlow among
freelancers and learners.
TensorFlow Packages
‘contrib’ package for more models
Support for higher level functions
Flipping a tensor along a dimension
and checking a tensor for NaN and
infinity
Fast Fourier transforms supported
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Serialization
Entire graph is saved as a protocol buffer
This includes parameters and operations
PyTorch has a simple API
The API saves all weights of all
the models
GO WITH THE FLOW!
Graph can be loaded in other
supported languages such as
C++ and Java.
Support for running old models
as well.
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Deployment
1
2
3
4
Mobile Deployments
TensorFlow is better for Mobile deployments.
Easier understanding of data flow in the
framework
Android and iOS
No need to rewrite the entire inference
portion of the model in Java or C++
Availability of TensorBoard.
Small Scale Applications
For small scale server-side deployments
both frameworks are easy to wrap
For example, Flask web server.
High Performance
TensorFlow serving can be used for server-side
deployments.
Models can be swapped easily without bringing the
service down.
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Documentation
01 02 03
API Documentation
Python APIs are very
well documented
Lot of examples and
tutorials to learn
both PyTorch and
TensorFlow
Lot of learners and
support.
More results for
use-cases and
tutorials.
Production support
Win-Win Situation
Everything can be
found in terms of
documentation for
both frameworks.
However, PyTorch C
library requires a
little more
documentation.
{ api }
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Device Management
PREFERENCE
TensorFlow is preferred for it’s seamless integration for everyone ranging
from beginners to the advanced users.
ASSUMPTION
By default, TensorFlow assumes you want to run the code on the GPU if
one is available.
MANUAL INTERVENTION
With PyTorch, everything need to be moved onto the device even if CUDA
is enabled.
ONE DOWNSIDE OF TENSORFLOW
By default, TensorFlow consumes all memory on all available GPUs even if only
one is being used.
04
03
02
01
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Custom Extensions
Win-Win
Compiling the extension is straightforward
with both frameworks.
No need for downloading any headers or
source code (All included in pip)
Building Custom Extension
Binding custom extensions written in C, C++ or
CUDA is doable with both frameworks
Depends on personal preference and the
organization which implements the models
TensorFlow requires more boilerplate
code
Support for multiples devices and
types
First, we need to write an interface
Then write implementation for each CPU and
GPU versions
Losswise can be used as an alternative to
TensorBoard
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Conclusion
Let’s conclude with opinions and the tiny details that matter!
Copyright © 2018, edureka and/or its affiliates. All rights reserved.
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
50% 50%
Conclusion – Optimism
TensorFlow
TensorFlow is better for large-
scale deployments
Good for cross-platform and
embedded deployment
Bigger community base and
many users
PyTorch
PyTorch is better for rapid
prototyping in Research.
Good start for hobbyists and
small-scale projects
Better utilization and
optimization for use of GPUs
AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow
Conclusion – My Opinion
TensorFlow is better for large-
scale deployments
Good for cross-platform and
embedded deployment
Bigger community base and
many users
PyTorch
PyTorch is better for rapid
prototyping in Research.
Good start for hobbyists and
small-scale projects
Better utilization and
optimization for use of GPUs 65%
35%
TensorFlow
Copyright © 2018, edureka and/or its affiliates. All rights reserved.
PyTorch vs TensorFlow: The Force Is Strong With Which One? | Which One You Should Learn? | Edureka

More Related Content

What's hot

Data Science Training | Data Science For Beginners | Data Science With Python...
Data Science Training | Data Science For Beginners | Data Science With Python...Data Science Training | Data Science For Beginners | Data Science With Python...
Data Science Training | Data Science For Beginners | Data Science With Python...
Simplilearn
 

What's hot (20)

Practical sentiment analysis
Practical sentiment analysisPractical sentiment analysis
Practical sentiment analysis
 
Pytorch
PytorchPytorch
Pytorch
 
TensorFlow
TensorFlowTensorFlow
TensorFlow
 
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
PyTorch Python Tutorial | Deep Learning Using PyTorch | Image Classifier Usin...
 
Introduction To Tensorflow
Introduction To TensorflowIntroduction To Tensorflow
Introduction To Tensorflow
 
Attention is All You Need (Transformer)
Attention is All You Need (Transformer)Attention is All You Need (Transformer)
Attention is All You Need (Transformer)
 
Information retrieval 9 tf idf weights
Information retrieval 9 tf idf weightsInformation retrieval 9 tf idf weights
Information retrieval 9 tf idf weights
 
Machine Learning Ml Overview Algorithms Use Cases And Applications
Machine Learning Ml Overview Algorithms Use Cases And ApplicationsMachine Learning Ml Overview Algorithms Use Cases And Applications
Machine Learning Ml Overview Algorithms Use Cases And Applications
 
Introduction to Keras
Introduction to KerasIntroduction to Keras
Introduction to Keras
 
Deep Learning With Python Tutorial | Edureka
Deep Learning With Python Tutorial | EdurekaDeep Learning With Python Tutorial | Edureka
Deep Learning With Python Tutorial | Edureka
 
Multilayer tutorial-netsci2014-slightlyupdated
Multilayer tutorial-netsci2014-slightlyupdatedMultilayer tutorial-netsci2014-slightlyupdated
Multilayer tutorial-netsci2014-slightlyupdated
 
Python & jupyter notebook installation
Python & jupyter notebook installationPython & jupyter notebook installation
Python & jupyter notebook installation
 
Recurrent and Recursive Nets (part 2)
Recurrent and Recursive Nets (part 2)Recurrent and Recursive Nets (part 2)
Recurrent and Recursive Nets (part 2)
 
Deep learning with tensorflow
Deep learning with tensorflowDeep learning with tensorflow
Deep learning with tensorflow
 
Keras and TensorFlow
Keras and TensorFlowKeras and TensorFlow
Keras and TensorFlow
 
Keras Tutorial For Beginners | Creating Deep Learning Models Using Keras In P...
Keras Tutorial For Beginners | Creating Deep Learning Models Using Keras In P...Keras Tutorial For Beginners | Creating Deep Learning Models Using Keras In P...
Keras Tutorial For Beginners | Creating Deep Learning Models Using Keras In P...
 
TensorFlow and Keras: An Overview
TensorFlow and Keras: An OverviewTensorFlow and Keras: An Overview
TensorFlow and Keras: An Overview
 
Introduction To TensorFlow
Introduction To TensorFlowIntroduction To TensorFlow
Introduction To TensorFlow
 
Introduction to using google colab
Introduction to using google colabIntroduction to using google colab
Introduction to using google colab
 
Data Science Training | Data Science For Beginners | Data Science With Python...
Data Science Training | Data Science For Beginners | Data Science With Python...Data Science Training | Data Science For Beginners | Data Science With Python...
Data Science Training | Data Science For Beginners | Data Science With Python...
 

Similar to PyTorch vs TensorFlow: The Force Is Strong With Which One? | Which One You Should Learn? | Edureka

Deep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Deep Learning Neural Network Acceleration at the Edge - Andrea GalloDeep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Deep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Linaro
 
“Khronos Group Standards: Powering the Future of Embedded Vision,” a Presenta...
“Khronos Group Standards: Powering the Future of Embedded Vision,” a Presenta...“Khronos Group Standards: Powering the Future of Embedded Vision,” a Presenta...
“Khronos Group Standards: Powering the Future of Embedded Vision,” a Presenta...
Edge AI and Vision Alliance
 

Similar to PyTorch vs TensorFlow: The Force Is Strong With Which One? | Which One You Should Learn? | Edureka (20)

TensorFlow meetup: Keras - Pytorch - TensorFlow.js
TensorFlow meetup: Keras - Pytorch - TensorFlow.jsTensorFlow meetup: Keras - Pytorch - TensorFlow.js
TensorFlow meetup: Keras - Pytorch - TensorFlow.js
 
Austin,TX Meetup presentation tensorflow final oct 26 2017
Austin,TX Meetup presentation tensorflow final oct 26 2017Austin,TX Meetup presentation tensorflow final oct 26 2017
Austin,TX Meetup presentation tensorflow final oct 26 2017
 
How to Run TensorFlow Cheaper in the Cloud Using Elastic GPUs
How to Run TensorFlow Cheaper in the Cloud Using Elastic GPUsHow to Run TensorFlow Cheaper in the Cloud Using Elastic GPUs
How to Run TensorFlow Cheaper in the Cloud Using Elastic GPUs
 
"Update on Khronos Standards for Vision and Machine Learning," a Presentation...
"Update on Khronos Standards for Vision and Machine Learning," a Presentation..."Update on Khronos Standards for Vision and Machine Learning," a Presentation...
"Update on Khronos Standards for Vision and Machine Learning," a Presentation...
 
Deep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Deep Learning Neural Network Acceleration at the Edge - Andrea GalloDeep Learning Neural Network Acceleration at the Edge - Andrea Gallo
Deep Learning Neural Network Acceleration at the Edge - Andrea Gallo
 
Tensorflow Ecosystem
Tensorflow EcosystemTensorflow Ecosystem
Tensorflow Ecosystem
 
Top 8 Deep Learning Frameworks | Which Deep Learning Framework You Should Lea...
Top 8 Deep Learning Frameworks | Which Deep Learning Framework You Should Lea...Top 8 Deep Learning Frameworks | Which Deep Learning Framework You Should Lea...
Top 8 Deep Learning Frameworks | Which Deep Learning Framework You Should Lea...
 
Innovation with ai at scale on the edge vt sept 2019 v0
Innovation with ai at scale  on the edge vt sept 2019 v0Innovation with ai at scale  on the edge vt sept 2019 v0
Innovation with ai at scale on the edge vt sept 2019 v0
 
Hadoop training in mumbai
Hadoop training in mumbaiHadoop training in mumbai
Hadoop training in mumbai
 
“Khronos Standard APIs for Accelerating Vision and Inferencing,” a Presentati...
“Khronos Standard APIs for Accelerating Vision and Inferencing,” a Presentati...“Khronos Standard APIs for Accelerating Vision and Inferencing,” a Presentati...
“Khronos Standard APIs for Accelerating Vision and Inferencing,” a Presentati...
 
Machine learning and Deep learning on edge devices using TensorFlow
Machine learning and Deep learning on edge devices using TensorFlowMachine learning and Deep learning on edge devices using TensorFlow
Machine learning and Deep learning on edge devices using TensorFlow
 
Simplify Machine Learning with the Deep Learning AMI | AWS Floor28
Simplify Machine Learning with the Deep Learning AMI | AWS Floor28Simplify Machine Learning with the Deep Learning AMI | AWS Floor28
Simplify Machine Learning with the Deep Learning AMI | AWS Floor28
 
Deep Learning with Spark and GPUs
Deep Learning with Spark and GPUsDeep Learning with Spark and GPUs
Deep Learning with Spark and GPUs
 
Distributed Deep Learning with Keras and TensorFlow on Apache Spark
Distributed Deep Learning with Keras and TensorFlow on Apache SparkDistributed Deep Learning with Keras and TensorFlow on Apache Spark
Distributed Deep Learning with Keras and TensorFlow on Apache Spark
 
Deep Learning with Apache Spark and GPUs with Pierce Spitler
Deep Learning with Apache Spark and GPUs with Pierce SpitlerDeep Learning with Apache Spark and GPUs with Pierce Spitler
Deep Learning with Apache Spark and GPUs with Pierce Spitler
 
TDC2019 Intel Software Day - Tecnicas de Programacao Paralela em Machine Lear...
TDC2019 Intel Software Day - Tecnicas de Programacao Paralela em Machine Lear...TDC2019 Intel Software Day - Tecnicas de Programacao Paralela em Machine Lear...
TDC2019 Intel Software Day - Tecnicas de Programacao Paralela em Machine Lear...
 
"APIs for Accelerating Vision and Inferencing: An Industry Overview of Option...
"APIs for Accelerating Vision and Inferencing: An Industry Overview of Option..."APIs for Accelerating Vision and Inferencing: An Industry Overview of Option...
"APIs for Accelerating Vision and Inferencing: An Industry Overview of Option...
 
Tensorflow 2.0 and Coral Edge TPU
Tensorflow 2.0 and Coral Edge TPU Tensorflow 2.0 and Coral Edge TPU
Tensorflow 2.0 and Coral Edge TPU
 
“Khronos Group Standards: Powering the Future of Embedded Vision,” a Presenta...
“Khronos Group Standards: Powering the Future of Embedded Vision,” a Presenta...“Khronos Group Standards: Powering the Future of Embedded Vision,” a Presenta...
“Khronos Group Standards: Powering the Future of Embedded Vision,” a Presenta...
 
General Learning.pptx
General Learning.pptxGeneral Learning.pptx
General Learning.pptx
 

More from Edureka!

More from Edureka! (20)

What to learn during the 21 days Lockdown | Edureka
What to learn during the 21 days Lockdown | EdurekaWhat to learn during the 21 days Lockdown | Edureka
What to learn during the 21 days Lockdown | Edureka
 
Top 10 Dying Programming Languages in 2020 | Edureka
Top 10 Dying Programming Languages in 2020 | EdurekaTop 10 Dying Programming Languages in 2020 | Edureka
Top 10 Dying Programming Languages in 2020 | Edureka
 
Top 5 Trending Business Intelligence Tools | Edureka
Top 5 Trending Business Intelligence Tools | EdurekaTop 5 Trending Business Intelligence Tools | Edureka
Top 5 Trending Business Intelligence Tools | Edureka
 
Tableau Tutorial for Data Science | Edureka
Tableau Tutorial for Data Science | EdurekaTableau Tutorial for Data Science | Edureka
Tableau Tutorial for Data Science | Edureka
 
Python Programming Tutorial | Edureka
Python Programming Tutorial | EdurekaPython Programming Tutorial | Edureka
Python Programming Tutorial | Edureka
 
Top 5 PMP Certifications | Edureka
Top 5 PMP Certifications | EdurekaTop 5 PMP Certifications | Edureka
Top 5 PMP Certifications | Edureka
 
Top Maven Interview Questions in 2020 | Edureka
Top Maven Interview Questions in 2020 | EdurekaTop Maven Interview Questions in 2020 | Edureka
Top Maven Interview Questions in 2020 | Edureka
 
Linux Mint Tutorial | Edureka
Linux Mint Tutorial | EdurekaLinux Mint Tutorial | Edureka
Linux Mint Tutorial | Edureka
 
How to Deploy Java Web App in AWS| Edureka
How to Deploy Java Web App in AWS| EdurekaHow to Deploy Java Web App in AWS| Edureka
How to Deploy Java Web App in AWS| Edureka
 
Importance of Digital Marketing | Edureka
Importance of Digital Marketing | EdurekaImportance of Digital Marketing | Edureka
Importance of Digital Marketing | Edureka
 
RPA in 2020 | Edureka
RPA in 2020 | EdurekaRPA in 2020 | Edureka
RPA in 2020 | Edureka
 
Email Notifications in Jenkins | Edureka
Email Notifications in Jenkins | EdurekaEmail Notifications in Jenkins | Edureka
Email Notifications in Jenkins | Edureka
 
EA Algorithm in Machine Learning | Edureka
EA Algorithm in Machine Learning | EdurekaEA Algorithm in Machine Learning | Edureka
EA Algorithm in Machine Learning | Edureka
 
Cognitive AI Tutorial | Edureka
Cognitive AI Tutorial | EdurekaCognitive AI Tutorial | Edureka
Cognitive AI Tutorial | Edureka
 
AWS Cloud Practitioner Tutorial | Edureka
AWS Cloud Practitioner Tutorial | EdurekaAWS Cloud Practitioner Tutorial | Edureka
AWS Cloud Practitioner Tutorial | Edureka
 
Blue Prism Top Interview Questions | Edureka
Blue Prism Top Interview Questions | EdurekaBlue Prism Top Interview Questions | Edureka
Blue Prism Top Interview Questions | Edureka
 
Big Data on AWS Tutorial | Edureka
Big Data on AWS Tutorial | Edureka Big Data on AWS Tutorial | Edureka
Big Data on AWS Tutorial | Edureka
 
A star algorithm | A* Algorithm in Artificial Intelligence | Edureka
A star algorithm | A* Algorithm in Artificial Intelligence | EdurekaA star algorithm | A* Algorithm in Artificial Intelligence | Edureka
A star algorithm | A* Algorithm in Artificial Intelligence | Edureka
 
Kubernetes Installation on Ubuntu | Edureka
Kubernetes Installation on Ubuntu | EdurekaKubernetes Installation on Ubuntu | Edureka
Kubernetes Installation on Ubuntu | Edureka
 
Introduction to DevOps | Edureka
Introduction to DevOps | EdurekaIntroduction to DevOps | Edureka
Introduction to DevOps | Edureka
 

Recently uploaded

Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Victor Rentea
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 

Recently uploaded (20)

Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptx
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 

PyTorch vs TensorFlow: The Force Is Strong With Which One? | Which One You Should Learn? | Edureka

  • 1. Copyright © 2017, edureka and/or its affiliates. All rights reserved.
  • 2. Copyright © 2017, edureka and/or its affiliates. All rights reserved. Deep Learning Frameworks Let’s look highlights from PyTorch and TensorFlow Copyright © 2018, edureka and/or its affiliates. All rights reserved.
  • 3. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Deep Learning Frameworks Dynamic Computation Graphs Python Support Support for CUDA Easy to Use API Fast and Feels Native Actively used Visualizer Easily Trainable Layered Components Open Source Flexible Google
  • 4. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow PyTorch v/s TensorFlow An insight comparing both of the frameworks Copyright © 2018, edureka and/or its affiliates. All rights reserved.
  • 5. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Comparison Factors Deployment5 Documentation6 Device Management7 Custom Extensions8 Ramp-Up Time 1 Graph Creation 2 Coverage 3 Serialization 4
  • 6. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Ramp-Up Time PyTorch GPU enabled drop-in replacement for NumPy NumPy functionality makes it easier to learn TensorFlow TensorFlow code gets compiled into a graph by Python. TensorFlow Execution Engine is used. PyTorch PyTorch code is known for executing faster and more efficiently Not many extra concepts to learn. TensorFlow Extra concepts needed such as Session, Variable Scoping and Placeholders. More Boilerplate code needed 1 3 2 4
  • 7. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Graph Construction and Debugging PyTorch PyTorch TensorFlow TensorFlow Dynamic Computation Graphs Graphs can be built at runtime Graph construction is static Graphs need to be compiled first Debugging PyTorch is same as Python code pdb – Python Debugger can be used Learn TensorFlow debugger(tfdbg) – Extra! Request variables from session to inspect
  • 8. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Coverage Less features compared to TensorFlow Not as popular as TensorFlow among freelancers and learners. TensorFlow Packages ‘contrib’ package for more models Support for higher level functions Flipping a tensor along a dimension and checking a tensor for NaN and infinity Fast Fourier transforms supported
  • 9. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Serialization Entire graph is saved as a protocol buffer This includes parameters and operations PyTorch has a simple API The API saves all weights of all the models GO WITH THE FLOW! Graph can be loaded in other supported languages such as C++ and Java. Support for running old models as well.
  • 10. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Deployment 1 2 3 4 Mobile Deployments TensorFlow is better for Mobile deployments. Easier understanding of data flow in the framework Android and iOS No need to rewrite the entire inference portion of the model in Java or C++ Availability of TensorBoard. Small Scale Applications For small scale server-side deployments both frameworks are easy to wrap For example, Flask web server. High Performance TensorFlow serving can be used for server-side deployments. Models can be swapped easily without bringing the service down.
  • 11. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Documentation 01 02 03 API Documentation Python APIs are very well documented Lot of examples and tutorials to learn both PyTorch and TensorFlow Lot of learners and support. More results for use-cases and tutorials. Production support Win-Win Situation Everything can be found in terms of documentation for both frameworks. However, PyTorch C library requires a little more documentation. { api }
  • 12. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Device Management PREFERENCE TensorFlow is preferred for it’s seamless integration for everyone ranging from beginners to the advanced users. ASSUMPTION By default, TensorFlow assumes you want to run the code on the GPU if one is available. MANUAL INTERVENTION With PyTorch, everything need to be moved onto the device even if CUDA is enabled. ONE DOWNSIDE OF TENSORFLOW By default, TensorFlow consumes all memory on all available GPUs even if only one is being used. 04 03 02 01
  • 13. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Custom Extensions Win-Win Compiling the extension is straightforward with both frameworks. No need for downloading any headers or source code (All included in pip) Building Custom Extension Binding custom extensions written in C, C++ or CUDA is doable with both frameworks Depends on personal preference and the organization which implements the models TensorFlow requires more boilerplate code Support for multiples devices and types First, we need to write an interface Then write implementation for each CPU and GPU versions Losswise can be used as an alternative to TensorBoard
  • 14. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Conclusion Let’s conclude with opinions and the tiny details that matter! Copyright © 2018, edureka and/or its affiliates. All rights reserved.
  • 15. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow 50% 50% Conclusion – Optimism TensorFlow TensorFlow is better for large- scale deployments Good for cross-platform and embedded deployment Bigger community base and many users PyTorch PyTorch is better for rapid prototyping in Research. Good start for hobbyists and small-scale projects Better utilization and optimization for use of GPUs
  • 16. AI & Deep Learning Training www.edureka.co/ai-deep-learning-with-tensorflow Conclusion – My Opinion TensorFlow is better for large- scale deployments Good for cross-platform and embedded deployment Bigger community base and many users PyTorch PyTorch is better for rapid prototyping in Research. Good start for hobbyists and small-scale projects Better utilization and optimization for use of GPUs 65% 35% TensorFlow
  • 17. Copyright © 2018, edureka and/or its affiliates. All rights reserved.