Tweet
Tweet

Slide 1

Slide 1 text

How  to  deploy  Machine  Learning   models  in  the  Cloud Alex  Casalboni PYCON  SETTE   @  Firenze clda.co/pycon7-alex

Slide 2

Slide 2 text

About  Me PYCON  SETTE  @  FIRENZE @alex_casalboni clda.co/pycon7-alex Bachelor  in  Computer  Science Master  in  Sound  &  Music  Engineering 6+  years  of  Web  Development 3+  years  of  Python

Slide 3

Slide 3 text

Have  you  ever  met  a  Data  Scien@st? PYCON  SETTE  @  FIRENZE Bob Bob  leads  a  skilled  team  of  data  scienCsts Bob  has  built  a  great  ML  model Bob  loves  Python Bob  likes  user-­‐centered  ML clda.co/pycon7-alex

Slide 4

Slide 4 text

How  did  Bob  build  his  model  in  Python? PYCON  SETTE  @  FIRENZE clda.co/pycon7-code clda.co/pycon7-alex Bob

Slide 5

Slide 5 text

PYCON  SETTE  @  FIRENZE GPU  availability distributed  compuCng infrastructure-­‐aware  code 1.  Bob  needs  Elas@city clda.co/pycon7-alex And  why  is  deploying  a  challenge? Bob

Slide 6

Slide 6 text

PYCON  SETTE  @  FIRENZE MulC-­‐model  architecture A/B  tesCng  &  versioning RESTful  API 2.  Bob  needs  plenty  of  Features Auth  layer clda.co/pycon7-alex And  why  is  deploying  a  challenge? Bob

Slide 7

Slide 7 text

PYCON  SETTE  @  FIRENZE infrastructure  maintenance conCnuous  delivery  &  deployments automaCon,  performance  &  monitoring 3.  Data  Scien@sts  ain’t  DevOps ≠ clda.co/pycon7-alex And  why  is  deploying  a  challenge? Data   ScienCst DevOps

Slide 8

Slide 8 text

PYCON  SETTE  @  FIRENZE model  design,  training  &  tesCng code  reviews    &  debugging data  exploraCon 4.  DevOps  ain’t  Data  Scien@sts ≠ clda.co/pycon7-alex And  why  is  deploying  a  challenge? Data   ScienCst DevOps

Slide 9

Slide 9 text

Deployment  Strategies PYCON  SETTE  @  FIRENZE 1.  Web-­‐app  controller clda.co/pycon7-alex how  will  Bob  update  his  model(s)? same  website  auth  layer? shared  (limited)  uWSGI  processes? It’s  disarmingly  simple,  but… Bob

Slide 10

Slide 10 text

Deployment  Strategies PYCON  SETTE  @  FIRENZE 2.  Fleet  of  servers clda.co/pycon7-alex same  problems  as  before Bob  has  many  more  machines  to  maintain sCll  no  elasCcity  (over-­‐provisioning) Bigger  capacity  and  no  code  changes,  but… Bob Bob2 Bob3 Load  Balancing

Slide 11

Slide 11 text

Deployment  Strategies PYCON  SETTE  @  FIRENZE 3.  Auto  Scaling clda.co/pycon7-alex sCll  shared  resources?  containers? even  bigger  lack  of  ownership what  about  caching,  versioning  and  auth? Bob  achieved  elasCcity  and  availability  ,  but… AWS  ELB  +  Auto  Scaling   (or  maybe  ElasCc  Beanstalk?)

Slide 12

Slide 12 text

Deployment  Strategies PYCON  SETTE  @  FIRENZE 4.  Serverless clda.co/pycon7-alex + Amazon  API   Gateway AWS   Lambda Happy   Bob Infinite  scalability,  global  CDN  and  caching Transparent  elasCcity  (and  PAYG) RESTful  &  auth  layer  +  versioning  (for  free!) Bob  doesn’t  need  to  be  a  DevOps  anymore!

Slide 13

Slide 13 text

The  Serverless  Cloud PYCON  SETTE  @  FIRENZE clda.co/pycon7-alex There is always a server somewhere,
 you just don't have to worry about it :)

Slide 14

Slide 14 text

Does  Bob’s  code  change  a  lot? PYCON  SETTE  @  FIRENZE clda.co/pycon7-alex Basically,  no  change! Bob

Slide 15

Slide 15 text

How  does  Bob  keep  the  model  updated? PYCON  SETTE  @  FIRENZE clda.co/pycon7-alex Bob Hint:  use  gzip!

Slide 16

Slide 16 text

PYCON  SETTE  @  FIRENZE clda.co/pycon7-lambda clda.co/pycon7-alex

Slide 17

Slide 17 text

Serverless  Cloud  Domina@on PYCON  SETTE  @  FIRENZE Amazon  Web  Services  (Lambda) Microso`  Azure  (FuncCons) Google  Cloud  Plaborm  (FuncCons) IBM  Bluemix  (OpenWhisk) hook.io Cloud  PlaSorms Hybrid  &  Microservices stackhut.com webtask.io iron.io clda.co/pycon7-alex

Slide 18

Slide 18 text

Thank  you  :) jobs.cloudacademy.com P.S.  we  are  hiring!