SlideShare a Scribd company logo
ONNX and ONNX Runtime
By : Vishwas Narayan
Agenda
1. Introduction to the ONNX ecosystem
2. Production Usage
3. ONNX Technical Design
ML models : Research to production
Deployment
Data
Collection
Trainin
g
Inference
and
deployment
Conversion
ML models : Research to production
Deployment
Data
Collection
Trainin
g
Inference
and
deployment
Conversion
ML models : Research to production
Deployment
Data
Collection
Trainin
g
Inference
and
deployment
Conversion
ML models : Research to production
Deployment
Data
Collection
Trainin
g
Inference
and
deployment
Conversion
Data Storage
Collect
Transform
Normalize and other steps
Data from different source
Build a Model from Data
Deploy the Model
But in this form of research
ML engineers and Data Scientist will have some overlapping role.
ML
Engineer
Data
Scientist
Many Products use Machine Learning
We train using
Deployment Targets
We Train We Deploy
ONNX
ONNX is a machine learning model representation format that is open source.
ONNX establishes a standard set of operators - the building blocks of machine
learning and deep learning models - as well as a standard file format, allowing AI
developers to utilise models with a range of frameworks, tools, runtimes, and
compilers.
ONNX is now on
● Training - CPU,GPU
● Deployment - Edge/Mobile
How do I get an ONNX model?
1. ONNX Model Zoo
How do I get an ONNX model?
1. ONNX Model Zoo
2. Model creation service such as Azure Custom Vision and
AutoML
How do I get an ONNX model?
1. ONNX Model Zoo
2. Model creation service such as Azure Custom Vision and AutoML
3. Convert model from existing model from another framework
How do I get an ONNX model?
1. ONNX Model Zoo
2. Model creation service such as Azure Custom Vision and AutoML
3. Convert model from existing model from another framework
4. End to End machine Learning Service using an Azure Machine
Learning Service
And also you can get them from
Native Export from
● Pytorch and CNTK
● Converter
https://github.com/microsoft/OLive
ML models : Research to production
Deployment
Data
Collection
Trainin
g
Inference
and
deployment
Conversion
Inferencing of the Deep Learning Model
Model
Weights
ONNX Runtime
● Available for all platforms
● Hardware Vendors do provide support
https://github.com/microsoft/DirectML
https://github.com/onnx/tutorials
We Train We Deploy
ONNX runtime is available in
Product that leverage the ONNX model
So the Stats say it
https://www.onnxruntime.ai/docs/how-to/tune-performance.html
https://github.com/onnx/tutorials
Performance Metrics
● Accuracy
● Loss
● Recall
● Latency
Common results today are
● Word - Grammar Check
● Bing - Q/A
● Cognitive service
And many more
Technical Design Principles
● Should support new architecture
● Also be supportive for the traditional ML
● Backward Compatibility
● Compact
● Cross-Platform representation for Serialization
ONNX Specification
● ONNX is a open specification that consists of the following components:
● A definition of the extensible computation graph model
● Definition of Standard Data types
● Definition of the Build operation which is for the versioned operation
sert(Schema)
ONNX model File Format
Model
a. Version Info
b. Metadata
c. Acyclic Computation Data Flow Graph
ONNX model File Format
Graph
a. Input and output units
b. List of computational Node
c. Graph Name
ONNX model File Format
Computational Node
a. Zero to more input types of the design types
b. One or more output defined types
c. Operators
d. Operator Parameter
ONNX Supported Data Types
Tensor Data Type
● Int8,int16,int32,int64
● Uint8,uint16,uint32,uint64
● float16,float32,float64,float,double
● Bool
● String
● complex 64,complex128
ONNX Supported Data Types
Non Tensor Data TYpe
● Sequence
● Map
Operator in ONNX
https://github.com/onnx/onnx/blob/master/docs/Operators.md
● An operator is identified by <name,domain,version>
● Core ops (ONNX and ONNX-ML)
○ Should be supported by ONNX-compatible products
○ Generally cannot be meaningfully further decomposed
○ Currently 124 ops in ai.onnx domain and 18 in ai.onnx. ml
○ Supports many scenarios/problem areas including image classification,
recommendation,natural language processing,etc.
ONNX - Custom Ops
● Ops Specific to framework or runtime
● Indicated by custom domain name
● Primarily meant to be a safety valve
ONNX versioning
Done in 3 Levels
● IR version (file format) :Currenly at version %
● Opset Version ONNX Model declare which operator sets they require as a list
of the two-part-operator ids(domain,opset_version)
● Operator Verion: A given Operator is identified by a three
tuple(domain,Op_type,Op_version)
https://github.com/onnx/onnx/blob/master/docs/Versioning.md
And also the version do change
ONNX - Design Principles
● Provide complete implementation of the ONNX standard — implement all
versions of the operators (since opset 7)
● Backward compatibility
● High performance
● Cross platform
● Leverage custom accelerators and runtimes to enable maximum performance
(execution providers)
● Support hybrid execution of the models
● Extensible through pluggable modules
https://www.onnxruntime.ai/docs/resources/high-level-design.html
https://www.onnxruntime.ai/docs/resources/high-level-design.html
Graph Partitioning
Given a mutable graph, graph partitioner assigns graph nodes to each execution provider per their
capability and idea goal is to reach best performance in a heterogeneous environment.
ONNX RUNTIME uses a "greedy" node assignment mechanism
● Users specify a preferred execution provider list in order
● ONNX RUNTIME will go thru the list in order to check each provider's capability and assign nodes to
it if it can run the nodes.
FUTURE:
● Manual tuned partitioning
● ML based partitioning
Rewrite rule
An interface created for finding patterns (with specific nodes) and applying
rewriting rules against a sub-graph.
Graph Transformer
An interface created for applying graph transformation with full graph editing
capability.
Transformer Level 0
Transformers anyway will be applied after graph partitioning (e.g. cast insertion,
mem copy insertion)
Level 1: General transformers not specific to any specific execution provider (e.g.
drop out elimination)
Level 2: Execution provider specific transformers (e.g. transpose insertion for
FPGA)
Graph Optimizations
Level 0
Cast
MemCopy
https://gitee.com/arnoldfychen/onnxruntime/blob/master/docs/ONNX_Runtime_Pe
rf_Tuning.md
Graph Optimizations
Level 1
● Eliminateldentity
● EliminateSlice
● UnsqueezeElimination
● EliminateDropout
● FuseReluClip
● ShapeTolnitializer
● ConyAddFusion
● ConvMulFusion
● ConvBNFusion
Execution Provider
A hardware accelerator interface to query its capability and get corresponding executables.
● Kernel based execution providers
These execution providers provides implementations of operators defined in ONNX (e.g.
CPUExecutionProvider, CudaExecutionProvider, MKLDNNExecutionProvider, etc.)
● Runtime based execution providers
These execution providers may not have implementations with the granularity of ONNX ops, but it
can run whole or partial ONNX graph. Say, it can run several ONNX ops (a sub-graph) together
with one function it has (e.g. TensorRTExecutionProvider, nGraphExecutionProvider, etc.)
https://www.onnxruntime.ai/docs/reference/execution-providers/
Extending ONNX runtime
● Execution providers
○ Implement the lExecution Provider interface
■ Examples: TensorRT, OpenVino, NGraph, Android NNAPI, etc
● Custom operators
○ Support operators outside the ONNX standard
○ Support for writing custom ops in both C/C++ and Python
● Graph optimizers
○ Implement the Graph Transformer interface
ONNX Go Live(OLive)
● Automates the process of ONNX model shipping
● Integrates
○ model conversion
○ correctness test
○ performance tuning
into a single pipeline and outputs a production ready ONNX model with ONNX Runtime configurations
(execution provider + optimization options)
https://github.com/microsoft/OLive
So to know more you have to go to this link here
https://azure.microsoft.com/en-in/blog/onnx-runtime-is-now-open-source/
https://www.onnxruntime.ai/python/tutorial.html
Thank you

More Related Content

What's hot

PyTorch for Deep Learning Practitioners
PyTorch for Deep Learning PractitionersPyTorch for Deep Learning Practitioners
PyTorch for Deep Learning Practitioners
Bayu Aldi Yansyah
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
Lukas Masuch
 
What is MLOps
What is MLOpsWhat is MLOps
What is MLOps
Henrik Skogström
 
End to end Machine Learning using Kubeflow - Build, Train, Deploy and Manage
End to end Machine Learning using Kubeflow - Build, Train, Deploy and ManageEnd to end Machine Learning using Kubeflow - Build, Train, Deploy and Manage
End to end Machine Learning using Kubeflow - Build, Train, Deploy and Manage
Animesh Singh
 
Build Large-Scale Data Analytics and AI Pipeline Using RayDP
Build Large-Scale Data Analytics and AI Pipeline Using RayDPBuild Large-Scale Data Analytics and AI Pipeline Using RayDP
Build Large-Scale Data Analytics and AI Pipeline Using RayDP
Databricks
 
Fine tune and deploy Hugging Face NLP models
Fine tune and deploy Hugging Face NLP modelsFine tune and deploy Hugging Face NLP models
Fine tune and deploy Hugging Face NLP models
OVHcloud
 
TensorFlow Lite for mobile & IoT
TensorFlow Lite for mobile & IoT   TensorFlow Lite for mobile & IoT
TensorFlow Lite for mobile & IoT
Mia Chang
 
MLOps Using MLflow
MLOps Using MLflowMLOps Using MLflow
MLOps Using MLflow
Databricks
 
Introduction to Google Colaboratory.pdf
Introduction to Google Colaboratory.pdfIntroduction to Google Colaboratory.pdf
Introduction to Google Colaboratory.pdf
Yomna Mahmoud Ibrahim Hassan
 
Gocon2017:Goのロギング周りの考察
Gocon2017:Goのロギング周りの考察Gocon2017:Goのロギング周りの考察
Gocon2017:Goのロギング周りの考察
貴仁 大和屋
 
End-to-End Deep Learning Deployment with ONNX
End-to-End Deep Learning Deployment with ONNXEnd-to-End Deep Learning Deployment with ONNX
End-to-End Deep Learning Deployment with ONNX
Nick Pentreath
 
Build an LLM-powered application using LangChain.pdf
Build an LLM-powered application using LangChain.pdfBuild an LLM-powered application using LangChain.pdf
Build an LLM-powered application using LangChain.pdf
StephenAmell4
 
Ml ops past_present_future
Ml ops past_present_futureMl ops past_present_future
Ml ops past_present_future
Nisha Talagala
 
TensorFlow and Keras: An Overview
TensorFlow and Keras: An OverviewTensorFlow and Keras: An Overview
TensorFlow and Keras: An Overview
Poo Kuan Hoong
 
Apply MLOps at Scale
Apply MLOps at ScaleApply MLOps at Scale
Apply MLOps at Scale
Databricks
 
LLaMA 2.pptx
LLaMA 2.pptxLLaMA 2.pptx
LLaMA 2.pptx
RkRahul16
 
Thomas Wolf "An Introduction to Transfer Learning and Hugging Face"
Thomas Wolf "An Introduction to Transfer Learning and Hugging Face"Thomas Wolf "An Introduction to Transfer Learning and Hugging Face"
Thomas Wolf "An Introduction to Transfer Learning and Hugging Face"
Fwdays
 
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.pdf
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.pdfRetrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.pdf
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.pdf
Po-Chuan Chen
 
MLOps.pptx
MLOps.pptxMLOps.pptx
MLOps.pptx
AllenPeter7
 
Reinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face TransformersReinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face Transformers
Julien SIMON
 

What's hot (20)

PyTorch for Deep Learning Practitioners
PyTorch for Deep Learning PractitionersPyTorch for Deep Learning Practitioners
PyTorch for Deep Learning Practitioners
 
Deep learning - A Visual Introduction
Deep learning - A Visual IntroductionDeep learning - A Visual Introduction
Deep learning - A Visual Introduction
 
What is MLOps
What is MLOpsWhat is MLOps
What is MLOps
 
End to end Machine Learning using Kubeflow - Build, Train, Deploy and Manage
End to end Machine Learning using Kubeflow - Build, Train, Deploy and ManageEnd to end Machine Learning using Kubeflow - Build, Train, Deploy and Manage
End to end Machine Learning using Kubeflow - Build, Train, Deploy and Manage
 
Build Large-Scale Data Analytics and AI Pipeline Using RayDP
Build Large-Scale Data Analytics and AI Pipeline Using RayDPBuild Large-Scale Data Analytics and AI Pipeline Using RayDP
Build Large-Scale Data Analytics and AI Pipeline Using RayDP
 
Fine tune and deploy Hugging Face NLP models
Fine tune and deploy Hugging Face NLP modelsFine tune and deploy Hugging Face NLP models
Fine tune and deploy Hugging Face NLP models
 
TensorFlow Lite for mobile & IoT
TensorFlow Lite for mobile & IoT   TensorFlow Lite for mobile & IoT
TensorFlow Lite for mobile & IoT
 
MLOps Using MLflow
MLOps Using MLflowMLOps Using MLflow
MLOps Using MLflow
 
Introduction to Google Colaboratory.pdf
Introduction to Google Colaboratory.pdfIntroduction to Google Colaboratory.pdf
Introduction to Google Colaboratory.pdf
 
Gocon2017:Goのロギング周りの考察
Gocon2017:Goのロギング周りの考察Gocon2017:Goのロギング周りの考察
Gocon2017:Goのロギング周りの考察
 
End-to-End Deep Learning Deployment with ONNX
End-to-End Deep Learning Deployment with ONNXEnd-to-End Deep Learning Deployment with ONNX
End-to-End Deep Learning Deployment with ONNX
 
Build an LLM-powered application using LangChain.pdf
Build an LLM-powered application using LangChain.pdfBuild an LLM-powered application using LangChain.pdf
Build an LLM-powered application using LangChain.pdf
 
Ml ops past_present_future
Ml ops past_present_futureMl ops past_present_future
Ml ops past_present_future
 
TensorFlow and Keras: An Overview
TensorFlow and Keras: An OverviewTensorFlow and Keras: An Overview
TensorFlow and Keras: An Overview
 
Apply MLOps at Scale
Apply MLOps at ScaleApply MLOps at Scale
Apply MLOps at Scale
 
LLaMA 2.pptx
LLaMA 2.pptxLLaMA 2.pptx
LLaMA 2.pptx
 
Thomas Wolf "An Introduction to Transfer Learning and Hugging Face"
Thomas Wolf "An Introduction to Transfer Learning and Hugging Face"Thomas Wolf "An Introduction to Transfer Learning and Hugging Face"
Thomas Wolf "An Introduction to Transfer Learning and Hugging Face"
 
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.pdf
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.pdfRetrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.pdf
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.pdf
 
MLOps.pptx
MLOps.pptxMLOps.pptx
MLOps.pptx
 
Reinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face TransformersReinventing Deep Learning
 with Hugging Face Transformers
Reinventing Deep Learning
 with Hugging Face Transformers
 

Similar to Onnx and onnx runtime

Linux-Internals-and-Networking
Linux-Internals-and-NetworkingLinux-Internals-and-Networking
Linux-Internals-and-Networking
Emertxe Information Technologies Pvt Ltd
 
BKK16-106 ODP Project Update
BKK16-106 ODP Project UpdateBKK16-106 ODP Project Update
BKK16-106 ODP Project Update
Linaro
 
Oleksii Moskalenko "Continuous Delivery of ML Pipelines to Production"
Oleksii Moskalenko "Continuous Delivery of ML Pipelines to Production"Oleksii Moskalenko "Continuous Delivery of ML Pipelines to Production"
Oleksii Moskalenko "Continuous Delivery of ML Pipelines to Production"
Fwdays
 
Onnc intro
Onnc introOnnc intro
Onnc intro
Luba Tang
 
Explore asp.net core 3.0 features
Explore asp.net core 3.0 featuresExplore asp.net core 3.0 features
Explore asp.net core 3.0 features
iFour Technolab Pvt. Ltd.
 
OpenDataPlane Testing in Travis
OpenDataPlane Testing in TravisOpenDataPlane Testing in Travis
OpenDataPlane Testing in Travis
Dmitry Baryshkov
 
"APIs for Accelerating Vision and Inferencing: Options and Trade-offs," a Pre...
"APIs for Accelerating Vision and Inferencing: Options and Trade-offs," a Pre..."APIs for Accelerating Vision and Inferencing: Options and Trade-offs," a Pre...
"APIs for Accelerating Vision and Inferencing: Options and Trade-offs," a Pre...
Edge AI and Vision Alliance
 
EclipseCon Eu 2015 - Breathe life into your Designer!
EclipseCon Eu 2015 - Breathe life into your Designer!EclipseCon Eu 2015 - Breathe life into your Designer!
EclipseCon Eu 2015 - Breathe life into your Designer!
melbats
 
Heterogeneous multiprocessing on androd and i.mx7
Heterogeneous multiprocessing on androd and i.mx7Heterogeneous multiprocessing on androd and i.mx7
Heterogeneous multiprocessing on androd and i.mx7
Kynetics
 
.NET Core, ASP.NET Core Course, Session 3
.NET Core, ASP.NET Core Course, Session 3.NET Core, ASP.NET Core Course, Session 3
.NET Core, ASP.NET Core Course, Session 3
aminmesbahi
 
Hands on OpenCL
Hands on OpenCLHands on OpenCL
Hands on OpenCL
Vladimir Starostenkov
 
"New Standards for Embedded Vision and Neural Networks," a Presentation from ...
"New Standards for Embedded Vision and Neural Networks," a Presentation from ..."New Standards for Embedded Vision and Neural Networks," a Presentation from ...
"New Standards for Embedded Vision and Neural Networks," a Presentation from ...
Edge AI and Vision Alliance
 
Testing kubernetes and_open_shift_at_scale_20170209
Testing kubernetes and_open_shift_at_scale_20170209Testing kubernetes and_open_shift_at_scale_20170209
Testing kubernetes and_open_shift_at_scale_20170209
mffiedler
 
The Fn Project: A Quick Introduction (December 2017)
The Fn Project: A Quick Introduction (December 2017)The Fn Project: A Quick Introduction (December 2017)
The Fn Project: A Quick Introduction (December 2017)
Oracle Developers
 
.NET Applications & Cloud Meetup at 7 Peaks
.NET Applications & Cloud Meetup at 7 Peaks.NET Applications & Cloud Meetup at 7 Peaks
.NET Applications & Cloud Meetup at 7 Peaks
Seven Peaks Speaks
 
Learn more about the tremendous value Open Data Plane brings to NFV
Learn more about the tremendous value Open Data Plane brings to NFVLearn more about the tremendous value Open Data Plane brings to NFV
Learn more about the tremendous value Open Data Plane brings to NFV
Ghodhbane Mohamed Amine
 
20141111_SOS3_Gallo
20141111_SOS3_Gallo20141111_SOS3_Gallo
20141111_SOS3_GalloAndrea Gallo
 
TSC Sponsored BoF: Can Linux and Automotive Functional Safety Mix ? Take 2: T...
TSC Sponsored BoF: Can Linux and Automotive Functional Safety Mix ? Take 2: T...TSC Sponsored BoF: Can Linux and Automotive Functional Safety Mix ? Take 2: T...
TSC Sponsored BoF: Can Linux and Automotive Functional Safety Mix ? Take 2: T...
Linaro
 
SFO15-102:ODP Project Update
SFO15-102:ODP Project UpdateSFO15-102:ODP Project Update
SFO15-102:ODP Project Update
Linaro
 

Similar to Onnx and onnx runtime (20)

Linux-Internals-and-Networking
Linux-Internals-and-NetworkingLinux-Internals-and-Networking
Linux-Internals-and-Networking
 
BKK16-106 ODP Project Update
BKK16-106 ODP Project UpdateBKK16-106 ODP Project Update
BKK16-106 ODP Project Update
 
Oleksii Moskalenko "Continuous Delivery of ML Pipelines to Production"
Oleksii Moskalenko "Continuous Delivery of ML Pipelines to Production"Oleksii Moskalenko "Continuous Delivery of ML Pipelines to Production"
Oleksii Moskalenko "Continuous Delivery of ML Pipelines to Production"
 
Onnc intro
Onnc introOnnc intro
Onnc intro
 
Explore asp.net core 3.0 features
Explore asp.net core 3.0 featuresExplore asp.net core 3.0 features
Explore asp.net core 3.0 features
 
OpenDataPlane Testing in Travis
OpenDataPlane Testing in TravisOpenDataPlane Testing in Travis
OpenDataPlane Testing in Travis
 
"APIs for Accelerating Vision and Inferencing: Options and Trade-offs," a Pre...
"APIs for Accelerating Vision and Inferencing: Options and Trade-offs," a Pre..."APIs for Accelerating Vision and Inferencing: Options and Trade-offs," a Pre...
"APIs for Accelerating Vision and Inferencing: Options and Trade-offs," a Pre...
 
EclipseCon Eu 2015 - Breathe life into your Designer!
EclipseCon Eu 2015 - Breathe life into your Designer!EclipseCon Eu 2015 - Breathe life into your Designer!
EclipseCon Eu 2015 - Breathe life into your Designer!
 
Heterogeneous multiprocessing on androd and i.mx7
Heterogeneous multiprocessing on androd and i.mx7Heterogeneous multiprocessing on androd and i.mx7
Heterogeneous multiprocessing on androd and i.mx7
 
.NET Core, ASP.NET Core Course, Session 3
.NET Core, ASP.NET Core Course, Session 3.NET Core, ASP.NET Core Course, Session 3
.NET Core, ASP.NET Core Course, Session 3
 
Hands on OpenCL
Hands on OpenCLHands on OpenCL
Hands on OpenCL
 
"New Standards for Embedded Vision and Neural Networks," a Presentation from ...
"New Standards for Embedded Vision and Neural Networks," a Presentation from ..."New Standards for Embedded Vision and Neural Networks," a Presentation from ...
"New Standards for Embedded Vision and Neural Networks," a Presentation from ...
 
Testing kubernetes and_open_shift_at_scale_20170209
Testing kubernetes and_open_shift_at_scale_20170209Testing kubernetes and_open_shift_at_scale_20170209
Testing kubernetes and_open_shift_at_scale_20170209
 
The Fn Project: A Quick Introduction (December 2017)
The Fn Project: A Quick Introduction (December 2017)The Fn Project: A Quick Introduction (December 2017)
The Fn Project: A Quick Introduction (December 2017)
 
.NET Applications & Cloud Meetup at 7 Peaks
.NET Applications & Cloud Meetup at 7 Peaks.NET Applications & Cloud Meetup at 7 Peaks
.NET Applications & Cloud Meetup at 7 Peaks
 
Learn more about the tremendous value Open Data Plane brings to NFV
Learn more about the tremendous value Open Data Plane brings to NFVLearn more about the tremendous value Open Data Plane brings to NFV
Learn more about the tremendous value Open Data Plane brings to NFV
 
20141111_SOS3_Gallo
20141111_SOS3_Gallo20141111_SOS3_Gallo
20141111_SOS3_Gallo
 
TSC Sponsored BoF: Can Linux and Automotive Functional Safety Mix ? Take 2: T...
TSC Sponsored BoF: Can Linux and Automotive Functional Safety Mix ? Take 2: T...TSC Sponsored BoF: Can Linux and Automotive Functional Safety Mix ? Take 2: T...
TSC Sponsored BoF: Can Linux and Automotive Functional Safety Mix ? Take 2: T...
 
Sudha Madhuri Yagnamurthy Resume 2 (5)
Sudha Madhuri Yagnamurthy Resume 2 (5)Sudha Madhuri Yagnamurthy Resume 2 (5)
Sudha Madhuri Yagnamurthy Resume 2 (5)
 
SFO15-102:ODP Project Update
SFO15-102:ODP Project UpdateSFO15-102:ODP Project Update
SFO15-102:ODP Project Update
 

More from Vishwas N

API Testing and Hacking.pdf
API Testing and Hacking.pdfAPI Testing and Hacking.pdf
API Testing and Hacking.pdf
Vishwas N
 
API Hijacking.pdf
API Hijacking.pdfAPI Hijacking.pdf
API Hijacking.pdf
Vishwas N
 
What should be your approach for solving ML_CV problem statements_.pdf
What should be your approach for solving ML_CV problem statements_.pdfWhat should be your approach for solving ML_CV problem statements_.pdf
What should be your approach for solving ML_CV problem statements_.pdf
Vishwas N
 
Deepfence.pdf
Deepfence.pdfDeepfence.pdf
Deepfence.pdf
Vishwas N
 
DevOps - A Purpose for an Institution.pdf
DevOps - A Purpose for an Institution.pdfDevOps - A Purpose for an Institution.pdf
DevOps - A Purpose for an Institution.pdf
Vishwas N
 
API Testing and Hacking (1).pdf
API Testing and Hacking (1).pdfAPI Testing and Hacking (1).pdf
API Testing and Hacking (1).pdf
Vishwas N
 
API Hijacking (1).pdf
API Hijacking (1).pdfAPI Hijacking (1).pdf
API Hijacking (1).pdf
Vishwas N
 
Dapr.pdf
Dapr.pdfDapr.pdf
Dapr.pdf
Vishwas N
 
linkerd.pdf
linkerd.pdflinkerd.pdf
linkerd.pdf
Vishwas N
 
HoloLens.pdf
HoloLens.pdfHoloLens.pdf
HoloLens.pdf
Vishwas N
 
Automated Governance for the DevOps Institutions.pdf
Automated Governance for the DevOps Institutions.pdfAutomated Governance for the DevOps Institutions.pdf
Automated Governance for the DevOps Institutions.pdf
Vishwas N
 
Lets build with DevSecOps Culture.pdf
Lets build with DevSecOps Culture.pdfLets build with DevSecOps Culture.pdf
Lets build with DevSecOps Culture.pdf
Vishwas N
 
Github Actions and Terraform.pdf
Github Actions and Terraform.pdfGithub Actions and Terraform.pdf
Github Actions and Terraform.pdf
Vishwas N
 
KEDA.pdf
KEDA.pdfKEDA.pdf
KEDA.pdf
Vishwas N
 
Ram bleed the hardware based approach for the hackers
Ram bleed the hardware based approach for the hackersRam bleed the hardware based approach for the hackers
Ram bleed the hardware based approach for the hackers
Vishwas N
 
Container on azure
Container on azureContainer on azure
Container on azure
Vishwas N
 
Deeplearning and dev ops azure
Deeplearning and dev ops azureDeeplearning and dev ops azure
Deeplearning and dev ops azure
Vishwas N
 
Azure data lakes
Azure data lakesAzure data lakes
Azure data lakes
Vishwas N
 
Azure dev ops
Azure dev opsAzure dev ops
Azure dev ops
Vishwas N
 
Azure ai on premises with docker
Azure ai on premises with  dockerAzure ai on premises with  docker
Azure ai on premises with docker
Vishwas N
 

More from Vishwas N (20)

API Testing and Hacking.pdf
API Testing and Hacking.pdfAPI Testing and Hacking.pdf
API Testing and Hacking.pdf
 
API Hijacking.pdf
API Hijacking.pdfAPI Hijacking.pdf
API Hijacking.pdf
 
What should be your approach for solving ML_CV problem statements_.pdf
What should be your approach for solving ML_CV problem statements_.pdfWhat should be your approach for solving ML_CV problem statements_.pdf
What should be your approach for solving ML_CV problem statements_.pdf
 
Deepfence.pdf
Deepfence.pdfDeepfence.pdf
Deepfence.pdf
 
DevOps - A Purpose for an Institution.pdf
DevOps - A Purpose for an Institution.pdfDevOps - A Purpose for an Institution.pdf
DevOps - A Purpose for an Institution.pdf
 
API Testing and Hacking (1).pdf
API Testing and Hacking (1).pdfAPI Testing and Hacking (1).pdf
API Testing and Hacking (1).pdf
 
API Hijacking (1).pdf
API Hijacking (1).pdfAPI Hijacking (1).pdf
API Hijacking (1).pdf
 
Dapr.pdf
Dapr.pdfDapr.pdf
Dapr.pdf
 
linkerd.pdf
linkerd.pdflinkerd.pdf
linkerd.pdf
 
HoloLens.pdf
HoloLens.pdfHoloLens.pdf
HoloLens.pdf
 
Automated Governance for the DevOps Institutions.pdf
Automated Governance for the DevOps Institutions.pdfAutomated Governance for the DevOps Institutions.pdf
Automated Governance for the DevOps Institutions.pdf
 
Lets build with DevSecOps Culture.pdf
Lets build with DevSecOps Culture.pdfLets build with DevSecOps Culture.pdf
Lets build with DevSecOps Culture.pdf
 
Github Actions and Terraform.pdf
Github Actions and Terraform.pdfGithub Actions and Terraform.pdf
Github Actions and Terraform.pdf
 
KEDA.pdf
KEDA.pdfKEDA.pdf
KEDA.pdf
 
Ram bleed the hardware based approach for the hackers
Ram bleed the hardware based approach for the hackersRam bleed the hardware based approach for the hackers
Ram bleed the hardware based approach for the hackers
 
Container on azure
Container on azureContainer on azure
Container on azure
 
Deeplearning and dev ops azure
Deeplearning and dev ops azureDeeplearning and dev ops azure
Deeplearning and dev ops azure
 
Azure data lakes
Azure data lakesAzure data lakes
Azure data lakes
 
Azure dev ops
Azure dev opsAzure dev ops
Azure dev ops
 
Azure ai on premises with docker
Azure ai on premises with  dockerAzure ai on premises with  docker
Azure ai on premises with docker
 

Recently uploaded

Latest trends in computer networking.pptx
Latest trends in computer networking.pptxLatest trends in computer networking.pptx
Latest trends in computer networking.pptx
JungkooksNonexistent
 
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
keoku
 
How to Use Contact Form 7 Like a Pro.pptx
How to Use Contact Form 7 Like a Pro.pptxHow to Use Contact Form 7 Like a Pro.pptx
How to Use Contact Form 7 Like a Pro.pptx
Gal Baras
 
History+of+E-commerce+Development+in+China-www.cfye-commerce.shop
History+of+E-commerce+Development+in+China-www.cfye-commerce.shopHistory+of+E-commerce+Development+in+China-www.cfye-commerce.shop
History+of+E-commerce+Development+in+China-www.cfye-commerce.shop
laozhuseo02
 
Internet-Security-Safeguarding-Your-Digital-World (1).pptx
Internet-Security-Safeguarding-Your-Digital-World (1).pptxInternet-Security-Safeguarding-Your-Digital-World (1).pptx
Internet-Security-Safeguarding-Your-Digital-World (1).pptx
VivekSinghShekhawat2
 
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
3ipehhoa
 
This 7-second Brain Wave Ritual Attracts Money To You.!
This 7-second Brain Wave Ritual Attracts Money To You.!This 7-second Brain Wave Ritual Attracts Money To You.!
This 7-second Brain Wave Ritual Attracts Money To You.!
nirahealhty
 
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
3ipehhoa
 
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
APNIC
 
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdfJAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
Javier Lasa
 
Comptia N+ Standard Networking lesson guide
Comptia N+ Standard Networking lesson guideComptia N+ Standard Networking lesson guide
Comptia N+ Standard Networking lesson guide
GTProductions1
 
1.Wireless Communication System_Wireless communication is a broad term that i...
1.Wireless Communication System_Wireless communication is a broad term that i...1.Wireless Communication System_Wireless communication is a broad term that i...
1.Wireless Communication System_Wireless communication is a broad term that i...
JeyaPerumal1
 
The+Prospects+of+E-Commerce+in+China.pptx
The+Prospects+of+E-Commerce+in+China.pptxThe+Prospects+of+E-Commerce+in+China.pptx
The+Prospects+of+E-Commerce+in+China.pptx
laozhuseo02
 
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
3ipehhoa
 
guildmasters guide to ravnica Dungeons & Dragons 5...
guildmasters guide to ravnica Dungeons & Dragons 5...guildmasters guide to ravnica Dungeons & Dragons 5...
guildmasters guide to ravnica Dungeons & Dragons 5...
Rogerio Filho
 
test test test test testtest test testtest test testtest test testtest test ...
test test  test test testtest test testtest test testtest test testtest test ...test test  test test testtest test testtest test testtest test testtest test ...
test test test test testtest test testtest test testtest test testtest test ...
Arif0071
 
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptxBridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
Brad Spiegel Macon GA
 
Multi-cluster Kubernetes Networking- Patterns, Projects and Guidelines
Multi-cluster Kubernetes Networking- Patterns, Projects and GuidelinesMulti-cluster Kubernetes Networking- Patterns, Projects and Guidelines
Multi-cluster Kubernetes Networking- Patterns, Projects and Guidelines
Sanjeev Rampal
 
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
ufdana
 
BASIC C++ lecture NOTE C++ lecture 3.pptx
BASIC C++ lecture NOTE C++ lecture 3.pptxBASIC C++ lecture NOTE C++ lecture 3.pptx
BASIC C++ lecture NOTE C++ lecture 3.pptx
natyesu
 

Recently uploaded (20)

Latest trends in computer networking.pptx
Latest trends in computer networking.pptxLatest trends in computer networking.pptx
Latest trends in computer networking.pptx
 
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
一比一原版(SLU毕业证)圣路易斯大学毕业证成绩单专业办理
 
How to Use Contact Form 7 Like a Pro.pptx
How to Use Contact Form 7 Like a Pro.pptxHow to Use Contact Form 7 Like a Pro.pptx
How to Use Contact Form 7 Like a Pro.pptx
 
History+of+E-commerce+Development+in+China-www.cfye-commerce.shop
History+of+E-commerce+Development+in+China-www.cfye-commerce.shopHistory+of+E-commerce+Development+in+China-www.cfye-commerce.shop
History+of+E-commerce+Development+in+China-www.cfye-commerce.shop
 
Internet-Security-Safeguarding-Your-Digital-World (1).pptx
Internet-Security-Safeguarding-Your-Digital-World (1).pptxInternet-Security-Safeguarding-Your-Digital-World (1).pptx
Internet-Security-Safeguarding-Your-Digital-World (1).pptx
 
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
1比1复刻(bath毕业证书)英国巴斯大学毕业证学位证原版一模一样
 
This 7-second Brain Wave Ritual Attracts Money To You.!
This 7-second Brain Wave Ritual Attracts Money To You.!This 7-second Brain Wave Ritual Attracts Money To You.!
This 7-second Brain Wave Ritual Attracts Money To You.!
 
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
急速办(bedfordhire毕业证书)英国贝德福特大学毕业证成绩单原版一模一样
 
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
APNIC Foundation, presented by Ellisha Heppner at the PNG DNS Forum 2024
 
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdfJAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
JAVIER LASA-EXPERIENCIA digital 1986-2024.pdf
 
Comptia N+ Standard Networking lesson guide
Comptia N+ Standard Networking lesson guideComptia N+ Standard Networking lesson guide
Comptia N+ Standard Networking lesson guide
 
1.Wireless Communication System_Wireless communication is a broad term that i...
1.Wireless Communication System_Wireless communication is a broad term that i...1.Wireless Communication System_Wireless communication is a broad term that i...
1.Wireless Communication System_Wireless communication is a broad term that i...
 
The+Prospects+of+E-Commerce+in+China.pptx
The+Prospects+of+E-Commerce+in+China.pptxThe+Prospects+of+E-Commerce+in+China.pptx
The+Prospects+of+E-Commerce+in+China.pptx
 
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
原版仿制(uob毕业证书)英国伯明翰大学毕业证本科学历证书原版一模一样
 
guildmasters guide to ravnica Dungeons & Dragons 5...
guildmasters guide to ravnica Dungeons & Dragons 5...guildmasters guide to ravnica Dungeons & Dragons 5...
guildmasters guide to ravnica Dungeons & Dragons 5...
 
test test test test testtest test testtest test testtest test testtest test ...
test test  test test testtest test testtest test testtest test testtest test ...test test  test test testtest test testtest test testtest test testtest test ...
test test test test testtest test testtest test testtest test testtest test ...
 
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptxBridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
Bridging the Digital Gap Brad Spiegel Macon, GA Initiative.pptx
 
Multi-cluster Kubernetes Networking- Patterns, Projects and Guidelines
Multi-cluster Kubernetes Networking- Patterns, Projects and GuidelinesMulti-cluster Kubernetes Networking- Patterns, Projects and Guidelines
Multi-cluster Kubernetes Networking- Patterns, Projects and Guidelines
 
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
一比一原版(CSU毕业证)加利福尼亚州立大学毕业证成绩单专业办理
 
BASIC C++ lecture NOTE C++ lecture 3.pptx
BASIC C++ lecture NOTE C++ lecture 3.pptxBASIC C++ lecture NOTE C++ lecture 3.pptx
BASIC C++ lecture NOTE C++ lecture 3.pptx
 

Onnx and onnx runtime

  • 1. ONNX and ONNX Runtime By : Vishwas Narayan
  • 2. Agenda 1. Introduction to the ONNX ecosystem 2. Production Usage 3. ONNX Technical Design
  • 3. ML models : Research to production Deployment Data Collection Trainin g Inference and deployment Conversion
  • 4. ML models : Research to production Deployment Data Collection Trainin g Inference and deployment Conversion
  • 5. ML models : Research to production Deployment Data Collection Trainin g Inference and deployment Conversion
  • 6. ML models : Research to production Deployment Data Collection Trainin g Inference and deployment Conversion
  • 7. Data Storage Collect Transform Normalize and other steps Data from different source Build a Model from Data Deploy the Model
  • 8. But in this form of research ML engineers and Data Scientist will have some overlapping role.
  • 10. Many Products use Machine Learning
  • 13. We Train We Deploy
  • 14. ONNX ONNX is a machine learning model representation format that is open source. ONNX establishes a standard set of operators - the building blocks of machine learning and deep learning models - as well as a standard file format, allowing AI developers to utilise models with a range of frameworks, tools, runtimes, and compilers.
  • 15. ONNX is now on ● Training - CPU,GPU ● Deployment - Edge/Mobile
  • 16. How do I get an ONNX model? 1. ONNX Model Zoo
  • 17. How do I get an ONNX model? 1. ONNX Model Zoo 2. Model creation service such as Azure Custom Vision and AutoML
  • 18. How do I get an ONNX model? 1. ONNX Model Zoo 2. Model creation service such as Azure Custom Vision and AutoML 3. Convert model from existing model from another framework
  • 19. How do I get an ONNX model? 1. ONNX Model Zoo 2. Model creation service such as Azure Custom Vision and AutoML 3. Convert model from existing model from another framework 4. End to End machine Learning Service using an Azure Machine Learning Service
  • 20. And also you can get them from Native Export from ● Pytorch and CNTK ● Converter https://github.com/microsoft/OLive
  • 21. ML models : Research to production Deployment Data Collection Trainin g Inference and deployment Conversion
  • 22. Inferencing of the Deep Learning Model Model Weights
  • 23. ONNX Runtime ● Available for all platforms ● Hardware Vendors do provide support https://github.com/microsoft/DirectML https://github.com/onnx/tutorials
  • 24. We Train We Deploy
  • 25.
  • 26. ONNX runtime is available in
  • 27. Product that leverage the ONNX model
  • 28.
  • 29. So the Stats say it https://www.onnxruntime.ai/docs/how-to/tune-performance.html https://github.com/onnx/tutorials
  • 30. Performance Metrics ● Accuracy ● Loss ● Recall ● Latency
  • 31. Common results today are ● Word - Grammar Check ● Bing - Q/A ● Cognitive service And many more
  • 32. Technical Design Principles ● Should support new architecture ● Also be supportive for the traditional ML ● Backward Compatibility ● Compact ● Cross-Platform representation for Serialization
  • 33. ONNX Specification ● ONNX is a open specification that consists of the following components: ● A definition of the extensible computation graph model ● Definition of Standard Data types ● Definition of the Build operation which is for the versioned operation sert(Schema)
  • 34. ONNX model File Format Model a. Version Info b. Metadata c. Acyclic Computation Data Flow Graph
  • 35. ONNX model File Format Graph a. Input and output units b. List of computational Node c. Graph Name
  • 36. ONNX model File Format Computational Node a. Zero to more input types of the design types b. One or more output defined types c. Operators d. Operator Parameter
  • 37. ONNX Supported Data Types Tensor Data Type ● Int8,int16,int32,int64 ● Uint8,uint16,uint32,uint64 ● float16,float32,float64,float,double ● Bool ● String ● complex 64,complex128
  • 38. ONNX Supported Data Types Non Tensor Data TYpe ● Sequence ● Map
  • 39. Operator in ONNX https://github.com/onnx/onnx/blob/master/docs/Operators.md ● An operator is identified by <name,domain,version> ● Core ops (ONNX and ONNX-ML) ○ Should be supported by ONNX-compatible products ○ Generally cannot be meaningfully further decomposed ○ Currently 124 ops in ai.onnx domain and 18 in ai.onnx. ml ○ Supports many scenarios/problem areas including image classification, recommendation,natural language processing,etc.
  • 40. ONNX - Custom Ops ● Ops Specific to framework or runtime ● Indicated by custom domain name ● Primarily meant to be a safety valve
  • 41. ONNX versioning Done in 3 Levels ● IR version (file format) :Currenly at version % ● Opset Version ONNX Model declare which operator sets they require as a list of the two-part-operator ids(domain,opset_version) ● Operator Verion: A given Operator is identified by a three tuple(domain,Op_type,Op_version) https://github.com/onnx/onnx/blob/master/docs/Versioning.md And also the version do change
  • 42. ONNX - Design Principles ● Provide complete implementation of the ONNX standard — implement all versions of the operators (since opset 7) ● Backward compatibility ● High performance ● Cross platform ● Leverage custom accelerators and runtimes to enable maximum performance (execution providers) ● Support hybrid execution of the models ● Extensible through pluggable modules
  • 43.
  • 46. Graph Partitioning Given a mutable graph, graph partitioner assigns graph nodes to each execution provider per their capability and idea goal is to reach best performance in a heterogeneous environment. ONNX RUNTIME uses a "greedy" node assignment mechanism ● Users specify a preferred execution provider list in order ● ONNX RUNTIME will go thru the list in order to check each provider's capability and assign nodes to it if it can run the nodes. FUTURE: ● Manual tuned partitioning ● ML based partitioning
  • 47. Rewrite rule An interface created for finding patterns (with specific nodes) and applying rewriting rules against a sub-graph.
  • 48. Graph Transformer An interface created for applying graph transformation with full graph editing capability.
  • 49. Transformer Level 0 Transformers anyway will be applied after graph partitioning (e.g. cast insertion, mem copy insertion) Level 1: General transformers not specific to any specific execution provider (e.g. drop out elimination) Level 2: Execution provider specific transformers (e.g. transpose insertion for FPGA)
  • 51. Graph Optimizations Level 1 ● Eliminateldentity ● EliminateSlice ● UnsqueezeElimination ● EliminateDropout ● FuseReluClip ● ShapeTolnitializer ● ConyAddFusion ● ConvMulFusion ● ConvBNFusion
  • 52. Execution Provider A hardware accelerator interface to query its capability and get corresponding executables. ● Kernel based execution providers These execution providers provides implementations of operators defined in ONNX (e.g. CPUExecutionProvider, CudaExecutionProvider, MKLDNNExecutionProvider, etc.) ● Runtime based execution providers These execution providers may not have implementations with the granularity of ONNX ops, but it can run whole or partial ONNX graph. Say, it can run several ONNX ops (a sub-graph) together with one function it has (e.g. TensorRTExecutionProvider, nGraphExecutionProvider, etc.)
  • 54. Extending ONNX runtime ● Execution providers ○ Implement the lExecution Provider interface ■ Examples: TensorRT, OpenVino, NGraph, Android NNAPI, etc ● Custom operators ○ Support operators outside the ONNX standard ○ Support for writing custom ops in both C/C++ and Python ● Graph optimizers ○ Implement the Graph Transformer interface
  • 55. ONNX Go Live(OLive) ● Automates the process of ONNX model shipping ● Integrates ○ model conversion ○ correctness test ○ performance tuning into a single pipeline and outputs a production ready ONNX model with ONNX Runtime configurations (execution provider + optimization options) https://github.com/microsoft/OLive
  • 56. So to know more you have to go to this link here https://azure.microsoft.com/en-in/blog/onnx-runtime-is-now-open-source/ https://www.onnxruntime.ai/python/tutorial.html