Tweet
Tweet

Slide 1

Slide 1 text

No content

Slide 2

Slide 2 text

TensorFlow Playground! Deploying Your Model

Slide 3

Slide 3 text

Development Environment TensorFlow Serving Tensor Flow Game Development 01 02 03 04 Table of contents

Slide 4

Slide 4 text

Rufai! Mustapha Software Engineer

Slide 5

Slide 5 text

Tensorflow

Slide 6

Slide 6 text

What is TensorFlow? A) A high-level programming language B) A cloud computing platform C) An open-source machine learning framework D) A database management system

Slide 7

Slide 7 text

Which of the following is NOT a core component of TensorFlow? A) Tensors B) Graphs C) Sessions D) Loops

Slide 8

Slide 8 text

What is the primary data structure in TensorFlow? A) Lists B) Dictionaries C) Tensors D) Arrays

Slide 9

Slide 9 text

Agenda Environment For Deployment Platforms Deployment Frameworks

Slide 10

Slide 10 text

Platform 00

Slide 11

Slide 11 text

Web

Slide 12

Slide 12 text

Web - First

Slide 13

Slide 13 text

Web - Iris

Slide 14

Slide 14 text

Android

Slide 15

Slide 15 text

Deployment Environment 01

Slide 16

Slide 16 text

No content

Slide 17

Slide 17 text

No content

Slide 18

Slide 18 text

apt-get remove tensorflow-model-server

Slide 19

Slide 19 text

echo "deb http://storage.googleapis.com/tensorflow-serving-apt stable tensorflow-model-server tensorflow-model-server-universal" | tee /etc/apt/sources.list.d/tensorflow-serving.list && \ curl https://storage.googleapis.com/tensorflow-serving-apt/tensorflow- serving.release.pub.gpg | apt-key add -

Slide 20

Slide 20 text

No content

Slide 21

Slide 21 text

Deployment Architecture 02

Slide 22

Slide 22 text

A Web Deployment Architecture

Slide 23

Slide 23 text

A production requires more than code

Slide 24

Slide 24 text

A production requires more than code

Slide 25

Slide 25 text

TensorFlow Serving

Slide 26

Slide 26 text

What Is Serving?

Slide 27

Slide 27 text

TensorFlow Serving Flexibility

Slide 28

Slide 28 text

TensorFlow Serving Flexibility Compatibility

Slide 29

Slide 29 text

TensorFlow Serving Flexibility Compatibility High Performance

Slide 30

Slide 30 text

TensorFlow Serving Flexibility Compatibility High Performance Inference Framework

Slide 31

Slide 31 text

TensorFlow Serving Flexibility Compatibility High Performance Inference Framework GPU Acceleration

Slide 32

Slide 32 text

TensorFlow Serving Flexibility Compatibility High Performance Inference Framework Model Version Control and Monitoring

Slide 33

Slide 33 text

TensorFlow Serving Architecture

Slide 34

Slide 34 text

What Is Serving?

Slide 35

Slide 35 text

What is the main purpose of TensorFlow Serving? a) To train machine learning models b) To deploy and serve machine learning models in production c) To create neural networks d) To preprocess data for machine learning models

Slide 36

Slide 36 text

Which of the following is NOT a benefit of using TensorFlow Serving? a) Low latency and high throughput b) Supports multiple models and versions c) Automatically tunes hyperparameters of models d) Seamless integration with Docker and Kubernetes

Slide 37

Slide 37 text

TensorFlow Serving supports which two main communication protocols? a) HTTP and WebSockets b) RESTful API and gRPC c) SOAP and FTP d) TCP/IP and SSH

Slide 38

Slide 38 text

In TensorFlow Serving, which format is used to save a trained model for serving? a) CSV b) TensorFlow Lite c) SavedModel d) HDF5

Slide 39

Slide 39 text

Which of the following statements is TRUE about TensorFlow Serving's architecture? a) TensorFlow Serving handles model training and hyperparameter tuning b) TensorFlow Serving manages model loading, prediction requests, and model lifecycle c) TensorFlow Serving is only used for training models d) TensorFlow Serving requires models to be in the TensorFlow Lite format

Slide 40

Slide 40 text

No content

Slide 41

Slide 41 text

References

Slide 42

Slide 42 text

Does anyone have any questions? Twitter @iafur https://mrufai.com