Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Making Deployments Easy with TF Serving | TF Ev...
Search
Rishit Dagli
May 11, 2021
Programming
1
150
Making Deployments Easy with TF Serving | TF Everywhere India
My talk at TensorFlow Everywhere India
Rishit Dagli
May 11, 2021
Tweet
Share
More Decks by Rishit Dagli
See All by Rishit Dagli
Fantastic Models and Where to Find Them
rishitdagli
0
68
Plant AI: Project Showcase
rishitdagli
0
120
Deploying an ML Model as an API | Postman Student Summit
rishitdagli
0
86
APIs 101 with Postman
rishitdagli
0
72
Deploying Models to production with Azure ML | Scottish Summit
rishitdagli
1
79
Computer Vision with TensorFlow, Getting Started
rishitdagli
0
280
Teaching Your Models to Play Fair | Global AI Student Conf
rishitdagli
1
160
Deploying Models to Production with TF Serving
rishitdagli
1
190
Superpower Your Android apps with ML: Android 11 | Devfest 2020
rishitdagli
1
77
Other Decks in Programming
See All in Programming
Datadog Workflow Automation で圧倒的価値提供
showwin
1
310
Expoによるアプリ開発の現在地とReact Server Componentsが切り開く未来
yukukotani
2
220
メンテが命: PHPフレームワークのコンテナ化とアップグレード戦略
shunta27
0
320
変化の激しい時代における、こだわりのないエンジニアの強さ
satoshi256kbyte
0
110
Kotlinの開発でも AIをいい感じに使いたい / Making the Most of AI in Kotlin Development
kohii00
5
1.9k
Jakarta EE meets AI
ivargrimstad
0
690
新宿駅構内を三人称視点で探索してみる
satoshi7190
2
130
たのしいSocketのしくみ / Socket Under a Microscope
coe401_
8
1.4k
読まないコードリーディング術
hisaju
0
120
仕様変更に耐えるための"今の"DRY原則を考える
mkmk884
9
3.3k
1年目の私に伝えたい!テストコードを怖がらなくなるためのヒント/Tips for not being afraid of test code
push_gawa
1
650
Duke on CRaC with Jakarta EE
ivargrimstad
0
160
Featured
See All Featured
Navigating Team Friction
lara
183
15k
How to Ace a Technical Interview
jacobian
276
23k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
507
140k
Java REST API Framework Comparison - PWX 2021
mraible
29
8.4k
The Power of CSS Pseudo Elements
geoffreycrofte
75
5.5k
Music & Morning Musume
bryan
46
6.4k
Thoughts on Productivity
jonyablonski
69
4.5k
Documentation Writing (for coders)
carmenintech
68
4.6k
A designer walks into a library…
pauljervisheath
205
24k
The Pragmatic Product Professional
lauravandoore
32
6.4k
How To Stay Up To Date on Web Technology
chriscoyier
790
250k
Into the Great Unknown - MozCon
thekraken
35
1.6k
Transcript
Making Deployments Easy with TF Serving Rishit Dagli High School
TEDx, TED-Ed Speaker rishit_dagli Rishit-dagli
“Most models don’t get deployed.”
of models don’t get deployed. 90%
Source: Laurence Moroney
Source: Laurence Moroney
• High School Student • TEDx and Ted-Ed Speaker •
♡ Hackathons and competitions • ♡ Research • My coordinates - www.rishit.tech $whoami rishit_dagli Rishit-dagli
• Devs who have worked on Deep Learning Models (Keras)
• Devs looking for ways to put their model into production ready manner Ideal Audience
Why care about ML deployments? Source: memegenerator.net
None
• Package the model What things to take care of?
• Package the model • Post the model on Server
What things to take care of?
• Package the model • Post the model on Server
• Maintain the server What things to take care of?
• Package the model • Post the model on Server
• Maintain the server Auto-scale What things to take care of?
• Package the model • Post the model on Server
• Maintain the server Auto-scale What things to take care of?
• Package the model • Post the model on Server
• Maintain the server Auto-scale Global availability What things to take care of?
• Package the model • Post the model on Server
• Maintain the server Auto-scale Global availability Latency What things to take care of?
• Package the model • Post the model on Server
• Maintain the server • API What things to take care of?
• Package the model • Post the model on Server
• Maintain the server • API • Model Versioning What things to take care of?
Simple Deployments Why are they inefficient?
None
Simple Deployments Why are they inefficient? • No consistent API
• No model versioning • No mini-batching • Inefficient for large models Source: Hannes Hapke
TensorFlow Serving
TensorFlow Serving TensorFlow Data validation TensorFlow Transform TensorFlow Model Analysis
TensorFlow Serving TensorFlow Extended
• Part of TensorFlow Extended TensorFlow Serving
• Part of TensorFlow Extended • Used Internally at Google
TensorFlow Serving
• Part of TensorFlow Extended • Used Internally at Google
• Makes deployment a lot easier TensorFlow Serving
The Process
• The SavedModel format • Graph definitions as protocol buffer
Export Model
SavedModel Directory
auxiliary files e.g. vocabularies SavedModel Directory
auxiliary files e.g. vocabularies SavedModel Directory Variables
auxiliary files e.g. vocabularies SavedModel Directory Variables Graph definitions
TensorFlow Serving
TensorFlow Serving
TensorFlow Serving Also supports gRPC
TensorFlow Serving
TensorFlow Serving
TensorFlow Serving
TensorFlow Serving
Inference
• Consistent APIs • Supports simultaneously gRPC: 8500 REST: 8501
• No lists but lists of lists Inference
• No lists but lists of lists Inference
• JSON response • Can specify a particular version Inference
with REST Default URL http://{HOST}:8501/v1/ models/test Model Version http://{HOST}:8501/v1/ models/test/versions/ {MODEL_VERSION}: predict
• JSON response • Can specify a particular version Inference
with REST Default URL http://{HOST}:8501/v1/ models/test Model Version http://{HOST}:8501/v1/ models/test/versions/ {MODEL_VERSION}: predict Port Model name
Inference with REST
• Better connections • Data converted to protocol buffer •
Request types have designated type • Payload converted to base64 • Use gRPC stubs Inference with gRPC
Model Meta Information
• You have an API to get meta info •
Useful for model tracking in telementry systems • Provides model input/ outputs, signatures Model Meta Information
Model Meta Information http://{HOST}:8501/ v1/models/{MODEL_NAME} /versions/{MODEL_VERSION} /metadata
Batch Inferences
• Use hardware efficiently • Save costs and compute resources
• Take multiple requests process them together • Super cool😎 for large models Batch inferences
• max_batch_size • batch_timeout_micros • num_batch_threads • max_enqueued_batches • file_system_poll_wait
_seconds • tensorflow_session _paralellism • tensorflow_intra_op _parallelism Batch Inference Highly customizable
• Load configuration file on startup • Change parameters according
to use cases Batch Inference
Also take a look at...
• Kubeflow deployments • Data pre-processing on server🚅 • AI
Platform Predictions • Deployment on edge devices • Federated learning Also take a look at...
bit.ly/tf-everywhere-ind Demos!
bit.ly/serving-deck Slides
Thank You rishit_dagli Rishit-dagli