Hands-On Lab using Oracle Machine Learning Services on Autonomous Database

In this Hands on Lab users experienced the use of Oracle Machine Learning Services on Oracle Autonomous Database through several Labs.

OML Services extends OML functionality to support model deployment and model lifecycle management for both in-database OML models and third-party Open Neural Networks Exchange (ONNX) machine learning models via REST APIs.

The REST API for Oracle Machine Learning Services provides REST API endpoints hosted on Oracle Autonomous Database. These endpoints enable the storage of machine learning models along with its metadata, and the creation of scoring endpoints for the model.

These third-party classification or regression models can be built using tools that support the ONNX format, which includes packages like Scikit-learn and TensorFlow, among several others.

In addition, OML Services supports proprietary cognitive text capabilities, with capabilities for topic discovery, keywords, summary, sentiment, and feature extraction. The initial languages supported include English, Spanish, and French (based on a Wikipedia knowledgebase using embeddings).

OML Services cognitive image functionality, supported through the ONNX format third-party model deployment feature, supports scoring using images or tensors.

02:18 Agenda
02:58 Accessing the Live Labs
06:39 Introduction to Oracle Machine Learning Services
10:03 Labs Overview
10:58 Lab 1: Installation and configuration Postman for REST API
13:42 Launch Postman
14:26 Download and Import sample Postman collections for OML Services
17:08 Checking readiness of environments
18:23 Launching OML Workshop
20:08 Configure Postman environment for the Live Labs OML Service server
23:18 Lab 2: Getting the Token for Authorization of OML Services REST requests
31:32 Lab 3: Registering and Scoring with Oracle Machine Learning models
31:43 Lab 3.3 Store OML model
33:08 Lab 3.3 Download ZIP file and load sample model into Postman
37:13 Lab 3.8 Create REST endpoint for OML model
40:04 Lab 3.13 Scoring OML model (single and mini-batch)
44:34 Lab 3.18 Scoring OML model (with Prediction Details)
45:58 OML models resiliency to input data errors
47:56 Lab3: Bonus round: Registering a model to OML Services from OML AutoML UI
53:43 Creating an OML AutoML UI experiment
57:04 Registering the OML AutoML UI model into OML Services as REST endpoints
1:00:18 Lab 3.11 List all models now showing the model registered from OML AutoML UI
1:00:50 Lab 3.13 Scoring the model built with AutoML UI
1:01:30 Lab 4: Registering and Scoring with ML models in ONNX format
1:01:39 Lab 4.3 Store ONNX model
1:03:31 Lab 4.8 Create REST endpoint for ONNX ML model
1:03:51 Lab 4.13 Score ONNX ML model (single and mini-batch)
1:05:59 Lab 5: Registering and Scoring with Image Classification models in ONNX format
1:06:10 Lab 5.3 Store ONNX Image model
1:07:20 Lab 5.8 Create REST endpoint for ONNX Image model
1:07:58 Lab 5.13 Score ONNX Image model (single image and topN option)
1:11:09 Lab 6: Using OML Services Cognitive Text REST APIs
1:11:54 Lab 6.2 Cognitive text - English
1:15:49 Lab 6.8 Cognitive Text - Spanish
1:16:03 Lab 6.15 Cognitive text - French
1:17:09 Where to go from here?
1:18:15 Q&A

[mohanasaeed]

الف صلاة وسلام على سيدنا ونبينا وحبيبنا محمد 🌺

[rodionalukhanov]

first 20 minutes nothing happens. He shows meaningless slides and describes how to install postman. Then it takes 10 more minutes to get an access token. If you want to know, how OML Services work, go to 1:21:25.