SlideShare a Scribd company logo
1 of 92
Download to read offline
Lars Gregori, SAP CX
27.06.2019
SAP Stammtisch
SAP Leonardo Machine Learning
100% Stammtisch
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "2
►Image Processing
►Text Processing
►Similarity Scoring
►Re-Train and Bring Your Own Model
►Image Processing
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "4
API Business Hub - SAP Leonardo Machine Learning Foundation
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "5
• Inference Service for Customizable Image Classification
• Product Image Classification API
• Inference Service for Face Detection
• Inference Service for Human Detection
• Inference Service for Multi-Instance Image Segmentation
• Inference Service for Scene Text Recognition
• Inference Service for Optical Character Recognition (OCR)
Image Processing
Inference Service for Customizable Image Classification
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "7
Neuronal Net
Hidden-LayerInput-Layer
x×w11
+b11
x×w12
+b12
x×w13
+b13
x×w14
+b14
Output-Layer
Source: http://sappress.de/4795
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "8
CNN - Convolutional Layer
1 2
3 4
7 0
0 -1
3
Input Filter Output
Convolutional Layer Convolutional LayerConvolutional Kernel
Source: http://sappress.de/4795
Demo Image Classification
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "10
SDK and Code Snippet
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "11
https://api.sap.com/api/image_classification_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
07_Anwendungen_zur_Bilderkennung/07_01_ImageClassificationService (API)
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
07_Anwendungen_zur_Bilderkennung/07_01_ImageClassifierTest (SDK)
DEMO - Inference Service for Customizable Image Classification
Demo Product Image Classification API
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "13
https://api.sap.com/api/product_image_classification_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
07_Anwendungen_zur_Bilderkennung/07_01_ImageClassificationService (API)
DEMO - Product Image Classification API
Inference Service for Face Detection
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "15
Modern Face Recognition with Deep Learning
https://medium.com/@ageitgey/machine-learning-is-fun-part-4-modern-face-recognition-with-deep-
learning-c3cffc121d78
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "17
Feature Extraction
Source: http://sappress.de/4795
Demo Face Detection
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "19
https://api.sap.com/api/face_detection_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
07_Anwendungen_zur_Bilderkennung/07_03_FaceDetection
DEMO - Inference Service for Face Detection
Demo Inference Service for Human Detection
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "21
https://api.sap.com/api/human_detection_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
07_Anwendungen_zur_Bilderkennung/07_04_HumanDetection
DEMO - Inference Service for Human Detection
Inference Service for Multi-Instance Image Segmentation
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "23
Mask RCNN - https://github.com/matterport/Mask_RCNN
Inference Service for Scene Text Recognition
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "25
Inference Service for Scene Text Recognition
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "26
Scene Text Recognition (meter reader)
Demo Scene Text Recognition
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "28
https://api.sap.com/api/scene_text_recognition_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
07_Anwendungen_zur_Bilderkennung/07_06_SceneTextRecognition
DEMO - Inference Service for Scene Text Recognition
Inference Service for Optical Character Recognition (OCR)
Demo Optical Character Recognition (OCR)
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "31
https://api.sap.com/api/ocr_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
07_Anwendungen_zur_Bilderkennung/07_07_Ocr
DEMO - Inference Service for Optical Character Recognition (OCR)
►Text Processing
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "33
• Inference Service for Language Detection
• Inference Service for Machine Translation
• Product Text Classification API
• Inference Service for Topic Detection
Text Processing
Inference Service for Language Detection
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "35
LangID
Stand-alone language identification system
https://github.com/saffsd/langid.py
Inference Service for Language Detection
Demo Language Detection
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "37
https://api.sap.com/api/language_detection_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
08_Anwendungen_zur_Texterkennung/08_TextServices
DEMO - Inference Service for Language Detection
Inference Service for Machine Translation
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "39
https://api.sap.com/api/translation_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
08_Anwendungen_zur_Texterkennung/08_TextServices
DEMO - Inference Service for Machine Translation
Product Text Classification API
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "41
https://api.sap.com/api/product_text_classification_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
08_Anwendungen_zur_Texterkennung/08_TextServices
DEMO - Product Text Classification API
Inference Service for Topic Detection
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "43
https://api.sap.com/api/topic_detection_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
08_Anwendungen_zur_Texterkennung/08_PlayList
DEMO - Inference Service for Topic Detection
►Similarity Scoring
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "45
• Inference Service for Similarity Scoring
• Inference Service For Customizable Image Feature Extraction
• Inference Service for Document Feature Extraction
• Inference Service for Face Feature Extraction
Similarity Scoring
Inference Service for Similarity Scoring
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "47
Cosine Similarity
Theta
Demo Similarity Scoring
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "49
https://api.sap.com/api/similarity_scoring_api/resource
DEMO - Inference Service for Similarity Scoring
Inference Service for Document Feature Extraction
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "51
Inference Service for Document Feature Extraction
Source: http://sappress.de/4795
Demo Document Feature Extraction
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "53
https://api.sap.com/api/document_feature_extraction_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
09_Anwendungen_zur_Aehnlichkeitsbewertung/09_01_DocumentFeatureExtraction
DEMO - Inference Service for Document Feature Extraction
Inference Service for Face Feature Extraction
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "55
Modern Face Recognition with Deep Learning
https://medium.com/@ageitgey/machine-learning-is-fun-part-4-modern-face-recognition-with-deep-
learning-c3cffc121d78
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "56
Inference Service for Face Feature Extraction
Source: http://sappress.de/4795
Demo Face Feature Extraction
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "58
https://api.sap.com/api/face_feature_extraction_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
09_Anwendungen_zur_Aehnlichkeitsbewertung/09_02_FaceFeatureDetection
DEMO - Inference Service for Face Feature Extraction
Inference Service for Customizable Image Feature Extraction
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "60
Feature Extraction
Source: http://sappress.de/4795
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "61
Inference Service for Customizable Image Feature Extraction
Source: http://sappress.de/4795
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "62
Inference Service for Customizable Image Feature Extraction
Source: http://sappress.de/4795
Demo Customizable Image Feature Extraction
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "64
https://api.sap.com/api/img_feature_extraction_api/resource
https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/
09_Anwendungen_zur_Aehnlichkeitsbewertung/09_03_Shoes
DEMO - Inference Service for Customizable Image Feature Extraction
►Re-Train and Bring Your Own Model
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "66
• Activate SAP Leonardo ML on SCP Trial
• Re-Train Images
• Re-Train Text
• Bring Your Own Model (BYOM)
Re-Train and Bring Your Own Model
Activate SAP Leonardo ML on SCP Trial
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "68
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "69
Re-Train Images
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "71
Re-Train Images
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "72
https://blogs.sap.com/2018/11/04/retrain-an-image-classification-model-with-postman-and-sap-
leonardo-machine-learning-foundation-on-sap-cloud-platform-trial/
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "73
Re-Train Text
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "75
https://blogs.sap.com/2018/12/03/retrain-a-text-classification-with-postman-and-sap-leonardo-
machine-learning-foundation-on-sap-cloud-platform-trial-sentiment-analysis/
Bring Your Own Model (BYOM)
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "77
BYOM
http://sappress.de/4795
Deploy BYOM
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "79
BYOM - Deploy Modell
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "80
BYOM - Deploy Modell
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "81
BYOM - Deploy Modell
BYOM Cloud Foundry
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "83
applications:
- name: xor
memory: 1024M
buildpack: python_buildpack
command: python app.py
env:
MODEL_NAME: xor
MODEL_VERSION: 3
DEPLOYMENT_URL: https://mlfproduction-deployment-api.cfapps.eu10.hana.ondemand.com
services:
- ml
BYOM - manifest.yaml (Cloud Foundry)
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "84
grpcio==1.12.1
tensorflow==1.8.0
tensorflow-serving-api==1.8.0
requests
flask
BYOM - requirements.txt
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "85
deployment_url = DEPLOYMENT_URL + "/api/v2/modelServers"
token = globals.request.headers.get("Authorization")
headers = {

'Authorization': token,

'Cache-Control': "no-cache"

}
query = {"modelName": MODEL_NAME, "modelVersion": MODEL_VERSION}
response = requests.request("GET", deployment_url,
headers=headers, params=query)
model_info = json.loads(response.text)
BYOM - app.py
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "86
model_info = model_info["modelServers"][0]
endpoint = model_info["endpoints"][0]
credentials = implementations.ssl_channel_credentials(
root_certificates=str(endpoint["caCrt"]))
channel = implementations.secure_channel(
str(endpoint["host"]),
int(endpoint["port"]),
credentials)
BYOM - app.py
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "87
request = predict_pb2.PredictRequest()
request.model_spec.name = MODEL_NAME
request.model_spec.signature_name = 'serving_default'
tfutil = tf.contrib.util
t_proto = tfutil.make_tensor_proto(data, shape=[1, len(data)],
dtype="float")
request.inputs["dense_1_input:0"].CopyFrom(t_proto)
predict = stub.Predict(request)
res = predict.outputs['dense_2/Sigmoid:0'].float_val[0]
return str(res)
BYOM - app.py
Demo BYOM Application
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "89
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "90
BYOM Anwendung
Fiori App SCP Python App
Modell
Token/
Same-origin policy gRPC

caCrt
© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "91
http://sappress.de/4795
https://github.com/choas/sap-leonardo
Some Links
Contact information:
Lars Gregori
Technology Strategist
SAP Customer Experience Labs
@choas
Thank you.
http://sappress.de/4795

More Related Content

Similar to SAP Leonardo ML Services Demo

SAPPHIRE NOW 2018 ASUG 11652 SAP Screen Personas as part of the SAP Fiori UX
SAPPHIRE NOW 2018 ASUG 11652 SAP Screen Personas as part of the SAP Fiori UXSAPPHIRE NOW 2018 ASUG 11652 SAP Screen Personas as part of the SAP Fiori UX
SAPPHIRE NOW 2018 ASUG 11652 SAP Screen Personas as part of the SAP Fiori UXPeter Spielvogel
 
ASUG84544 - Workflow Solutions from SAP When to Use What.pdf
ASUG84544 - Workflow Solutions from SAP When to Use What.pdfASUG84544 - Workflow Solutions from SAP When to Use What.pdf
ASUG84544 - Workflow Solutions from SAP When to Use What.pdfssuser8bab641
 
ASUG webcast - going mobile with Slipstream Engine March 2018
ASUG webcast - going mobile with Slipstream Engine March 2018ASUG webcast - going mobile with Slipstream Engine March 2018
ASUG webcast - going mobile with Slipstream Engine March 2018Peter Spielvogel
 
Kyma: Extending Business systems with Kubernetes, Istio and <fill the blank>.
Kyma: Extending Business systems with Kubernetes, Istio and <fill the blank>.Kyma: Extending Business systems with Kubernetes, Istio and <fill the blank>.
Kyma: Extending Business systems with Kubernetes, Istio and <fill the blank>.SAP HANA Cloud Platform
 
SAP Cloud Platform x Microsoft Graph
SAP Cloud Platform x Microsoft GraphSAP Cloud Platform x Microsoft Graph
SAP Cloud Platform x Microsoft GraphMarius Obert
 
How SAP uses Flowable as its BPMN engine for SAP CP Workflow
How SAP uses Flowable as its BPMN engine for SAP CP WorkflowHow SAP uses Flowable as its BPMN engine for SAP CP Workflow
How SAP uses Flowable as its BPMN engine for SAP CP WorkflowFlowable
 
Quantify your drive: IoT on a personal scale with SAP technologies
Quantify your drive: IoT on a personal scale with SAP technologiesQuantify your drive: IoT on a personal scale with SAP technologies
Quantify your drive: IoT on a personal scale with SAP technologiesVitaliy Rudnytskiy
 
#askSAP Analytics Innovations Community Call: Delivering the Intelligent Ente...
#askSAP Analytics Innovations Community Call: Delivering the Intelligent Ente...#askSAP Analytics Innovations Community Call: Delivering the Intelligent Ente...
#askSAP Analytics Innovations Community Call: Delivering the Intelligent Ente...SAP Analytics
 
What is SAP API Management_.pdf
What is SAP API Management_.pdfWhat is SAP API Management_.pdf
What is SAP API Management_.pdfBilawalAmeen
 
Building cool native ios enterprise apps with sap cloud platform sdk for ios
Building cool native ios enterprise apps with sap cloud platform sdk for iosBuilding cool native ios enterprise apps with sap cloud platform sdk for ios
Building cool native ios enterprise apps with sap cloud platform sdk for iosNagesh Caparthy
 
Using a trained model on your mobile device
Using a trained model on your mobile deviceUsing a trained model on your mobile device
Using a trained model on your mobile deviceLars Gregori
 
Using a trained model on your mobile device
Using a trained model on your mobile deviceUsing a trained model on your mobile device
Using a trained model on your mobile deviceLars Gregori
 
Developing and Deploying Applications on the SAP HANA Platform
Developing and Deploying Applications on the SAP HANA PlatformDeveloping and Deploying Applications on the SAP HANA Platform
Developing and Deploying Applications on the SAP HANA PlatformVitaliy Rudnytskiy
 
Innovate and Extend with an Agile Digital Enterprise Platform
Innovate and Extend with an Agile Digital Enterprise PlatformInnovate and Extend with an Agile Digital Enterprise Platform
Innovate and Extend with an Agile Digital Enterprise PlatformVladimir Pavlov
 
SAP HANA Cloud Platform Community BOF @ Devoxx 2013
SAP HANA Cloud Platform Community BOF @ Devoxx 2013SAP HANA Cloud Platform Community BOF @ Devoxx 2013
SAP HANA Cloud Platform Community BOF @ Devoxx 2013SAP HANA Cloud Platform
 
SAP TechEd 2013: CD105: Extending SuccessFactors EmployeeCentral with apps on...
SAP TechEd 2013: CD105: Extending SuccessFactors EmployeeCentral with apps on...SAP TechEd 2013: CD105: Extending SuccessFactors EmployeeCentral with apps on...
SAP TechEd 2013: CD105: Extending SuccessFactors EmployeeCentral with apps on...SAP HANA Cloud Platform
 
SAP Developer Center - March 2016 update
SAP Developer Center - March 2016 updateSAP Developer Center - March 2016 update
SAP Developer Center - March 2016 updateVitaliy Rudnytskiy
 
Graph Pattern Matching in SAP HANA
Graph Pattern Matching in SAP HANAGraph Pattern Matching in SAP HANA
Graph Pattern Matching in SAP HANAopenCypher
 

Similar to SAP Leonardo ML Services Demo (20)

SAC AIN109_Presentation.pdf
SAC AIN109_Presentation.pdfSAC AIN109_Presentation.pdf
SAC AIN109_Presentation.pdf
 
SAPPHIRE NOW 2018 ASUG 11652 SAP Screen Personas as part of the SAP Fiori UX
SAPPHIRE NOW 2018 ASUG 11652 SAP Screen Personas as part of the SAP Fiori UXSAPPHIRE NOW 2018 ASUG 11652 SAP Screen Personas as part of the SAP Fiori UX
SAPPHIRE NOW 2018 ASUG 11652 SAP Screen Personas as part of the SAP Fiori UX
 
ASUG84544 - Workflow Solutions from SAP When to Use What.pdf
ASUG84544 - Workflow Solutions from SAP When to Use What.pdfASUG84544 - Workflow Solutions from SAP When to Use What.pdf
ASUG84544 - Workflow Solutions from SAP When to Use What.pdf
 
ASUG webcast - going mobile with Slipstream Engine March 2018
ASUG webcast - going mobile with Slipstream Engine March 2018ASUG webcast - going mobile with Slipstream Engine March 2018
ASUG webcast - going mobile with Slipstream Engine March 2018
 
Kyma: Extending Business systems with Kubernetes, Istio and <fill the blank>.
Kyma: Extending Business systems with Kubernetes, Istio and <fill the blank>.Kyma: Extending Business systems with Kubernetes, Istio and <fill the blank>.
Kyma: Extending Business systems with Kubernetes, Istio and <fill the blank>.
 
SAP Cloud Platform x Microsoft Graph
SAP Cloud Platform x Microsoft GraphSAP Cloud Platform x Microsoft Graph
SAP Cloud Platform x Microsoft Graph
 
How SAP uses Flowable as its BPMN engine for SAP CP Workflow
How SAP uses Flowable as its BPMN engine for SAP CP WorkflowHow SAP uses Flowable as its BPMN engine for SAP CP Workflow
How SAP uses Flowable as its BPMN engine for SAP CP Workflow
 
What the FaaS
What the FaaSWhat the FaaS
What the FaaS
 
Quantify your drive: IoT on a personal scale with SAP technologies
Quantify your drive: IoT on a personal scale with SAP technologiesQuantify your drive: IoT on a personal scale with SAP technologies
Quantify your drive: IoT on a personal scale with SAP technologies
 
#askSAP Analytics Innovations Community Call: Delivering the Intelligent Ente...
#askSAP Analytics Innovations Community Call: Delivering the Intelligent Ente...#askSAP Analytics Innovations Community Call: Delivering the Intelligent Ente...
#askSAP Analytics Innovations Community Call: Delivering the Intelligent Ente...
 
What is SAP API Management_.pdf
What is SAP API Management_.pdfWhat is SAP API Management_.pdf
What is SAP API Management_.pdf
 
Building cool native ios enterprise apps with sap cloud platform sdk for ios
Building cool native ios enterprise apps with sap cloud platform sdk for iosBuilding cool native ios enterprise apps with sap cloud platform sdk for ios
Building cool native ios enterprise apps with sap cloud platform sdk for ios
 
Using a trained model on your mobile device
Using a trained model on your mobile deviceUsing a trained model on your mobile device
Using a trained model on your mobile device
 
Using a trained model on your mobile device
Using a trained model on your mobile deviceUsing a trained model on your mobile device
Using a trained model on your mobile device
 
Developing and Deploying Applications on the SAP HANA Platform
Developing and Deploying Applications on the SAP HANA PlatformDeveloping and Deploying Applications on the SAP HANA Platform
Developing and Deploying Applications on the SAP HANA Platform
 
Innovate and Extend with an Agile Digital Enterprise Platform
Innovate and Extend with an Agile Digital Enterprise PlatformInnovate and Extend with an Agile Digital Enterprise Platform
Innovate and Extend with an Agile Digital Enterprise Platform
 
SAP HANA Cloud Platform Community BOF @ Devoxx 2013
SAP HANA Cloud Platform Community BOF @ Devoxx 2013SAP HANA Cloud Platform Community BOF @ Devoxx 2013
SAP HANA Cloud Platform Community BOF @ Devoxx 2013
 
SAP TechEd 2013: CD105: Extending SuccessFactors EmployeeCentral with apps on...
SAP TechEd 2013: CD105: Extending SuccessFactors EmployeeCentral with apps on...SAP TechEd 2013: CD105: Extending SuccessFactors EmployeeCentral with apps on...
SAP TechEd 2013: CD105: Extending SuccessFactors EmployeeCentral with apps on...
 
SAP Developer Center - March 2016 update
SAP Developer Center - March 2016 updateSAP Developer Center - March 2016 update
SAP Developer Center - March 2016 update
 
Graph Pattern Matching in SAP HANA
Graph Pattern Matching in SAP HANAGraph Pattern Matching in SAP HANA
Graph Pattern Matching in SAP HANA
 

More from Lars Gregori

BYOM - Bring Your Own Model
BYOM - Bring Your Own ModelBYOM - Bring Your Own Model
BYOM - Bring Your Own ModelLars Gregori
 
uTensor - embedded devices and machine learning models
uTensor - embedded devices and machine learning modelsuTensor - embedded devices and machine learning models
uTensor - embedded devices and machine learning modelsLars Gregori
 
Minecraft and reinforcement learning
Minecraft and reinforcement learningMinecraft and reinforcement learning
Minecraft and reinforcement learningLars Gregori
 
Machine Learning Models on Mobile Devices
Machine Learning Models on Mobile DevicesMachine Learning Models on Mobile Devices
Machine Learning Models on Mobile DevicesLars Gregori
 
Minecraft and Reinforcement Learning
Minecraft and Reinforcement LearningMinecraft and Reinforcement Learning
Minecraft and Reinforcement LearningLars Gregori
 
IoT protocolls - smart washing machine
IoT protocolls - smart washing machineIoT protocolls - smart washing machine
IoT protocolls - smart washing machineLars Gregori
 
[DE] AI und Minecraft
[DE] AI und Minecraft[DE] AI und Minecraft
[DE] AI und MinecraftLars Gregori
 
Minecraft and Reinforcement Learning
Minecraft and Reinforcement LearningMinecraft and Reinforcement Learning
Minecraft and Reinforcement LearningLars Gregori
 
[DE] IoT Protokolle
[DE] IoT Protokolle[DE] IoT Protokolle
[DE] IoT ProtokolleLars Gregori
 
[German] Boards für das IoT-Prototyping
[German] Boards für das IoT-Prototyping[German] Boards für das IoT-Prototyping
[German] Boards für das IoT-PrototypingLars Gregori
 
IoT, APIs und Microservices - alles unter Node-RED
IoT, APIs und Microservices - alles unter Node-REDIoT, APIs und Microservices - alles unter Node-RED
IoT, APIs und Microservices - alles unter Node-REDLars Gregori
 
Web Bluetooth - Next Generation Bluetooth?
Web Bluetooth - Next Generation Bluetooth?   Web Bluetooth - Next Generation Bluetooth?
Web Bluetooth - Next Generation Bluetooth? Lars Gregori
 
Embedded Rust – Rust on IoT devices
Embedded Rust – Rust on IoT devicesEmbedded Rust – Rust on IoT devices
Embedded Rust – Rust on IoT devicesLars Gregori
 
Embedded Rust on IoT devices
Embedded Rust on IoT devicesEmbedded Rust on IoT devices
Embedded Rust on IoT devicesLars Gregori
 
IoT mit Rust programmieren
IoT mit Rust programmierenIoT mit Rust programmieren
IoT mit Rust programmierenLars Gregori
 
Boards for the IoT-Prototyping
Boards for the IoT-PrototypingBoards for the IoT-Prototyping
Boards for the IoT-PrototypingLars Gregori
 
Groß steuert klein - Wie lässt sich ein Arduino steuern?
Groß steuert klein - Wie lässt sich ein Arduino steuern?Groß steuert klein - Wie lässt sich ein Arduino steuern?
Groß steuert klein - Wie lässt sich ein Arduino steuern?Lars Gregori
 
Connecting Minecraft and e-Commerce business services
Connecting Minecraft and e-Commerce business servicesConnecting Minecraft and e-Commerce business services
Connecting Minecraft and e-Commerce business servicesLars Gregori
 
Moto - Orchestrating IoT for business users 
and connecting it to YaaS
Moto - Orchestrating IoT for business users 
and connecting it to YaaSMoto - Orchestrating IoT for business users 
and connecting it to YaaS
Moto - Orchestrating IoT for business users 
and connecting it to YaaSLars Gregori
 

More from Lars Gregori (20)

BYOM - Bring Your Own Model
BYOM - Bring Your Own ModelBYOM - Bring Your Own Model
BYOM - Bring Your Own Model
 
uTensor - embedded devices and machine learning models
uTensor - embedded devices and machine learning modelsuTensor - embedded devices and machine learning models
uTensor - embedded devices and machine learning models
 
Minecraft and reinforcement learning
Minecraft and reinforcement learningMinecraft and reinforcement learning
Minecraft and reinforcement learning
 
Machine Learning Models on Mobile Devices
Machine Learning Models on Mobile DevicesMachine Learning Models on Mobile Devices
Machine Learning Models on Mobile Devices
 
Minecraft and Reinforcement Learning
Minecraft and Reinforcement LearningMinecraft and Reinforcement Learning
Minecraft and Reinforcement Learning
 
IoT protocolls - smart washing machine
IoT protocolls - smart washing machineIoT protocolls - smart washing machine
IoT protocolls - smart washing machine
 
[DE] AI und Minecraft
[DE] AI und Minecraft[DE] AI und Minecraft
[DE] AI und Minecraft
 
Minecraft and Reinforcement Learning
Minecraft and Reinforcement LearningMinecraft and Reinforcement Learning
Minecraft and Reinforcement Learning
 
[DE] IoT Protokolle
[DE] IoT Protokolle[DE] IoT Protokolle
[DE] IoT Protokolle
 
AI and Minecraft
AI and MinecraftAI and Minecraft
AI and Minecraft
 
[German] Boards für das IoT-Prototyping
[German] Boards für das IoT-Prototyping[German] Boards für das IoT-Prototyping
[German] Boards für das IoT-Prototyping
 
IoT, APIs und Microservices - alles unter Node-RED
IoT, APIs und Microservices - alles unter Node-REDIoT, APIs und Microservices - alles unter Node-RED
IoT, APIs und Microservices - alles unter Node-RED
 
Web Bluetooth - Next Generation Bluetooth?
Web Bluetooth - Next Generation Bluetooth?   Web Bluetooth - Next Generation Bluetooth?
Web Bluetooth - Next Generation Bluetooth?
 
Embedded Rust – Rust on IoT devices
Embedded Rust – Rust on IoT devicesEmbedded Rust – Rust on IoT devices
Embedded Rust – Rust on IoT devices
 
Embedded Rust on IoT devices
Embedded Rust on IoT devicesEmbedded Rust on IoT devices
Embedded Rust on IoT devices
 
IoT mit Rust programmieren
IoT mit Rust programmierenIoT mit Rust programmieren
IoT mit Rust programmieren
 
Boards for the IoT-Prototyping
Boards for the IoT-PrototypingBoards for the IoT-Prototyping
Boards for the IoT-Prototyping
 
Groß steuert klein - Wie lässt sich ein Arduino steuern?
Groß steuert klein - Wie lässt sich ein Arduino steuern?Groß steuert klein - Wie lässt sich ein Arduino steuern?
Groß steuert klein - Wie lässt sich ein Arduino steuern?
 
Connecting Minecraft and e-Commerce business services
Connecting Minecraft and e-Commerce business servicesConnecting Minecraft and e-Commerce business services
Connecting Minecraft and e-Commerce business services
 
Moto - Orchestrating IoT for business users 
and connecting it to YaaS
Moto - Orchestrating IoT for business users 
and connecting it to YaaSMoto - Orchestrating IoT for business users 
and connecting it to YaaS
Moto - Orchestrating IoT for business users 
and connecting it to YaaS
 

Recently uploaded

Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
Unlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsUnlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsPrecisely
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsAndrey Dotsenko
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 

Recently uploaded (20)

Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
Unlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power SystemsUnlocking the Potential of the Cloud for IBM Power Systems
Unlocking the Potential of the Cloud for IBM Power Systems
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 

SAP Leonardo ML Services Demo

  • 1. Lars Gregori, SAP CX 27.06.2019 SAP Stammtisch SAP Leonardo Machine Learning 100% Stammtisch
  • 2. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "2 ►Image Processing ►Text Processing ►Similarity Scoring ►Re-Train and Bring Your Own Model
  • 4. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "4 API Business Hub - SAP Leonardo Machine Learning Foundation
  • 5. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "5 • Inference Service for Customizable Image Classification • Product Image Classification API • Inference Service for Face Detection • Inference Service for Human Detection • Inference Service for Multi-Instance Image Segmentation • Inference Service for Scene Text Recognition • Inference Service for Optical Character Recognition (OCR) Image Processing
  • 6. Inference Service for Customizable Image Classification
  • 7. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "7 Neuronal Net Hidden-LayerInput-Layer x×w11 +b11 x×w12 +b12 x×w13 +b13 x×w14 +b14 Output-Layer Source: http://sappress.de/4795
  • 8. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "8 CNN - Convolutional Layer 1 2 3 4 7 0 0 -1 3 Input Filter Output Convolutional Layer Convolutional LayerConvolutional Kernel Source: http://sappress.de/4795
  • 10. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "10 SDK and Code Snippet
  • 11. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "11 https://api.sap.com/api/image_classification_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 07_Anwendungen_zur_Bilderkennung/07_01_ImageClassificationService (API) https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 07_Anwendungen_zur_Bilderkennung/07_01_ImageClassifierTest (SDK) DEMO - Inference Service for Customizable Image Classification
  • 12. Demo Product Image Classification API
  • 13. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "13 https://api.sap.com/api/product_image_classification_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 07_Anwendungen_zur_Bilderkennung/07_01_ImageClassificationService (API) DEMO - Product Image Classification API
  • 14. Inference Service for Face Detection
  • 15. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "15 Modern Face Recognition with Deep Learning https://medium.com/@ageitgey/machine-learning-is-fun-part-4-modern-face-recognition-with-deep- learning-c3cffc121d78
  • 16.
  • 17. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "17 Feature Extraction Source: http://sappress.de/4795
  • 19. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "19 https://api.sap.com/api/face_detection_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 07_Anwendungen_zur_Bilderkennung/07_03_FaceDetection DEMO - Inference Service for Face Detection
  • 20. Demo Inference Service for Human Detection
  • 21. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "21 https://api.sap.com/api/human_detection_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 07_Anwendungen_zur_Bilderkennung/07_04_HumanDetection DEMO - Inference Service for Human Detection
  • 22. Inference Service for Multi-Instance Image Segmentation
  • 23. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "23 Mask RCNN - https://github.com/matterport/Mask_RCNN
  • 24. Inference Service for Scene Text Recognition
  • 25. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "25 Inference Service for Scene Text Recognition
  • 26. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "26 Scene Text Recognition (meter reader)
  • 27. Demo Scene Text Recognition
  • 28. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "28 https://api.sap.com/api/scene_text_recognition_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 07_Anwendungen_zur_Bilderkennung/07_06_SceneTextRecognition DEMO - Inference Service for Scene Text Recognition
  • 29. Inference Service for Optical Character Recognition (OCR)
  • 30. Demo Optical Character Recognition (OCR)
  • 31. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "31 https://api.sap.com/api/ocr_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 07_Anwendungen_zur_Bilderkennung/07_07_Ocr DEMO - Inference Service for Optical Character Recognition (OCR)
  • 33. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "33 • Inference Service for Language Detection • Inference Service for Machine Translation • Product Text Classification API • Inference Service for Topic Detection Text Processing
  • 34. Inference Service for Language Detection
  • 35. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "35 LangID Stand-alone language identification system https://github.com/saffsd/langid.py Inference Service for Language Detection
  • 37. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "37 https://api.sap.com/api/language_detection_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 08_Anwendungen_zur_Texterkennung/08_TextServices DEMO - Inference Service for Language Detection
  • 38. Inference Service for Machine Translation
  • 39. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "39 https://api.sap.com/api/translation_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 08_Anwendungen_zur_Texterkennung/08_TextServices DEMO - Inference Service for Machine Translation
  • 41. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "41 https://api.sap.com/api/product_text_classification_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 08_Anwendungen_zur_Texterkennung/08_TextServices DEMO - Product Text Classification API
  • 42. Inference Service for Topic Detection
  • 43. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "43 https://api.sap.com/api/topic_detection_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 08_Anwendungen_zur_Texterkennung/08_PlayList DEMO - Inference Service for Topic Detection
  • 45. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "45 • Inference Service for Similarity Scoring • Inference Service For Customizable Image Feature Extraction • Inference Service for Document Feature Extraction • Inference Service for Face Feature Extraction Similarity Scoring
  • 46. Inference Service for Similarity Scoring
  • 47. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "47 Cosine Similarity Theta
  • 49. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "49 https://api.sap.com/api/similarity_scoring_api/resource DEMO - Inference Service for Similarity Scoring
  • 50. Inference Service for Document Feature Extraction
  • 51. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "51 Inference Service for Document Feature Extraction Source: http://sappress.de/4795
  • 52. Demo Document Feature Extraction
  • 53. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "53 https://api.sap.com/api/document_feature_extraction_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 09_Anwendungen_zur_Aehnlichkeitsbewertung/09_01_DocumentFeatureExtraction DEMO - Inference Service for Document Feature Extraction
  • 54. Inference Service for Face Feature Extraction
  • 55. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "55 Modern Face Recognition with Deep Learning https://medium.com/@ageitgey/machine-learning-is-fun-part-4-modern-face-recognition-with-deep- learning-c3cffc121d78
  • 56. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "56 Inference Service for Face Feature Extraction Source: http://sappress.de/4795
  • 57. Demo Face Feature Extraction
  • 58. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "58 https://api.sap.com/api/face_feature_extraction_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 09_Anwendungen_zur_Aehnlichkeitsbewertung/09_02_FaceFeatureDetection DEMO - Inference Service for Face Feature Extraction
  • 59. Inference Service for Customizable Image Feature Extraction
  • 60. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "60 Feature Extraction Source: http://sappress.de/4795
  • 61. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "61 Inference Service for Customizable Image Feature Extraction Source: http://sappress.de/4795
  • 62. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "62 Inference Service for Customizable Image Feature Extraction Source: http://sappress.de/4795
  • 63. Demo Customizable Image Feature Extraction
  • 64. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "64 https://api.sap.com/api/img_feature_extraction_api/resource https://github.com/choas/Machine-Learning-mit-SAP-Leonardo/tree/master/ 09_Anwendungen_zur_Aehnlichkeitsbewertung/09_03_Shoes DEMO - Inference Service for Customizable Image Feature Extraction
  • 65. ►Re-Train and Bring Your Own Model
  • 66. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "66 • Activate SAP Leonardo ML on SCP Trial • Re-Train Images • Re-Train Text • Bring Your Own Model (BYOM) Re-Train and Bring Your Own Model
  • 67. Activate SAP Leonardo ML on SCP Trial
  • 68. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "68
  • 69. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "69
  • 71. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "71 Re-Train Images
  • 72. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "72 https://blogs.sap.com/2018/11/04/retrain-an-image-classification-model-with-postman-and-sap- leonardo-machine-learning-foundation-on-sap-cloud-platform-trial/
  • 73. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "73
  • 75. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "75 https://blogs.sap.com/2018/12/03/retrain-a-text-classification-with-postman-and-sap-leonardo- machine-learning-foundation-on-sap-cloud-platform-trial-sentiment-analysis/
  • 76. Bring Your Own Model (BYOM)
  • 77. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "77 BYOM http://sappress.de/4795
  • 79. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "79 BYOM - Deploy Modell
  • 80. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "80 BYOM - Deploy Modell
  • 81. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "81 BYOM - Deploy Modell
  • 83. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "83 applications: - name: xor memory: 1024M buildpack: python_buildpack command: python app.py env: MODEL_NAME: xor MODEL_VERSION: 3 DEPLOYMENT_URL: https://mlfproduction-deployment-api.cfapps.eu10.hana.ondemand.com services: - ml BYOM - manifest.yaml (Cloud Foundry)
  • 84. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "84 grpcio==1.12.1 tensorflow==1.8.0 tensorflow-serving-api==1.8.0 requests flask BYOM - requirements.txt
  • 85. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "85 deployment_url = DEPLOYMENT_URL + "/api/v2/modelServers" token = globals.request.headers.get("Authorization") headers = {
 'Authorization': token,
 'Cache-Control': "no-cache"
 } query = {"modelName": MODEL_NAME, "modelVersion": MODEL_VERSION} response = requests.request("GET", deployment_url, headers=headers, params=query) model_info = json.loads(response.text) BYOM - app.py
  • 86. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "86 model_info = model_info["modelServers"][0] endpoint = model_info["endpoints"][0] credentials = implementations.ssl_channel_credentials( root_certificates=str(endpoint["caCrt"])) channel = implementations.secure_channel( str(endpoint["host"]), int(endpoint["port"]), credentials) BYOM - app.py
  • 87. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "87 request = predict_pb2.PredictRequest() request.model_spec.name = MODEL_NAME request.model_spec.signature_name = 'serving_default' tfutil = tf.contrib.util t_proto = tfutil.make_tensor_proto(data, shape=[1, len(data)], dtype="float") request.inputs["dense_1_input:0"].CopyFrom(t_proto) predict = stub.Predict(request) res = predict.outputs['dense_2/Sigmoid:0'].float_val[0] return str(res) BYOM - app.py
  • 89. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "89
  • 90. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "90 BYOM Anwendung Fiori App SCP Python App Modell Token/ Same-origin policy gRPC
 caCrt
  • 91. © 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "91 http://sappress.de/4795 https://github.com/choas/sap-leonardo Some Links
  • 92. Contact information: Lars Gregori Technology Strategist SAP Customer Experience Labs @choas Thank you. http://sappress.de/4795