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
160
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
75
Plant AI: Project Showcase
rishitdagli
0
120
Deploying an ML Model as an API | Postman Student Summit
rishitdagli
0
89
APIs 101 with Postman
rishitdagli
0
78
Deploying Models to production with Azure ML | Scottish Summit
rishitdagli
1
87
Computer Vision with TensorFlow, Getting Started
rishitdagli
0
290
Teaching Your Models to Play Fair | Global AI Student Conf
rishitdagli
1
170
Deploying Models to Production with TF Serving
rishitdagli
1
200
Superpower Your Android apps with ML: Android 11 | Devfest 2020
rishitdagli
1
81
Other Decks in Programming
See All in Programming
Cline指示通りに動かない? AI小説エージェントで学ぶ指示書の書き方と自動アップデートの仕組み
kamomeashizawa
1
580
すべてのコンテキストを、 ユーザー価値に変える
applism118
2
930
PicoRuby on Rails
makicamel
2
110
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
47
31k
第9回 情シス転職ミートアップ 株式会社IVRy(アイブリー)の紹介
ivry_presentationmaterials
1
240
Result型で“失敗”を型にするPHPコードの書き方
kajitack
4
510
ふつうの技術スタックでアート作品を作ってみる
akira888
0
170
プロダクト志向なエンジニアがもう一歩先の価値を目指すために意識したこと
nealle
0
110
AWS CDKの推しポイント 〜CloudFormationと比較してみた〜
akihisaikeda
3
320
Kotlin エンジニアへ送る:Swift 案件に参加させられる日に備えて~似てるけど色々違う Swift の仕様 / from Kotlin to Swift
lovee
1
260
プロダクト志向ってなんなんだろうね
righttouch
PRO
0
170
What Spring Developers Should Know About Jakarta EE
ivargrimstad
0
300
Featured
See All Featured
Optimizing for Happiness
mojombo
379
70k
Side Projects
sachag
455
42k
Rebuilding a faster, lazier Slack
samanthasiow
82
9.1k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
Practical Orchestrator
shlominoach
188
11k
The World Runs on Bad Software
bkeepers
PRO
69
11k
Keith and Marios Guide to Fast Websites
keithpitt
411
22k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
1.8k
It's Worth the Effort
3n
185
28k
Bash Introduction
62gerente
614
210k
Unsuck your backbone
ammeep
671
58k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
26k
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