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
#kanrk08 / 公開版 PicoRubyとマイコンでの自作トレーニング計測装置を用いたワークアウトの理想と現実
bash0c7
1
530
AIプログラマーDevinは PHPerの夢を見るか?
shinyasaita
1
170
GitHub Copilot and GitHub Codespaces Hands-on
ymd65536
1
120
PHPでWebSocketサーバーを実装しよう2025
kubotak
0
210
既存デザインを変更せずにタップ領域を広げる方法
tahia910
1
240
Webの外へ飛び出せ NativePHPが切り拓くPHPの未来
takuyakatsusa
2
430
VS Code Update for GitHub Copilot
74th
1
410
iOSアプリ開発で 関数型プログラミングを実現する The Composable Architectureの紹介
yimajo
2
220
5つのアンチパターンから学ぶLT設計
narihara
1
120
関数型まつり2025登壇資料「関数プログラミングと再帰」
taisontsukada
2
850
関数型まつりレポート for JuliaTokai #22
antimon2
0
160
Hypervel - A Coroutine Framework for Laravel Artisans
albertcht
1
100
Featured
See All Featured
Large-scale JavaScript Application Architecture
addyosmani
512
110k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
31
1.2k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
138
34k
GitHub's CSS Performance
jonrohan
1031
460k
StorybookのUI Testing Handbookを読んだ
zakiyama
30
5.8k
The Straight Up "How To Draw Better" Workshop
denniskardys
234
140k
Building Flexible Design Systems
yeseniaperezcruz
328
39k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
Docker and Python
trallard
44
3.4k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
31
2.4k
What’s in a name? Adding method to the madness
productmarketing
PRO
23
3.5k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
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