Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
ADS v2.15.0
Light Logo Dark Logo
ADS v2.15.0

Getting Started

  • Release Notes
  • Quick Start

Installation and Configuration

  • Installation and Setup
  • Authentication
  • CLI Configuration
  • Local Development Environment Setup
    • Build Development Container Image
    • Setting up Visual Studio Code
    • Working with Conda packs
    • Build Your Own Container (BYOC)
    • Local Job Execution
    • Local Pipeline Execution
    • Local Model Deployment Execution

AI Quick Actions API Server

  • AI Quick Actions API Server

Low-Code AI Operators

  • What Are Operators
  • AI Forecast Operator
    • Quick Start
    • Data Integration
    • Scalability
    • Multivariate Forecast
    • Installation
    • Development
    • Will the Forecast Operator Work for My Use Case?
    • YAML Schema
    • FAQs
  • Anomaly Detection
    • Quick Start
    • Will the Anomaly Detection Operator Work for My Use Case?
    • Installation
    • Productionize
    • Advanced Use Cases
    • YAML Schema
    • FAQs
  • Regression Operator
    • Quick Start
    • Installation
    • YAML Schema
    • Advanced Use Cases
    • Productionize
    • FAQ
  • PII
    • Installing the PII Operator
    • Getting Started
    • Configure PII
    • Examples
    • YAML Schema
  • Recommender
    • Quick Start
    • YAML Schema
    • Scalability
  • More About Operators
    • IAM Policies
    • Explore & Configure Operators
    • How To Run

Tasks

  • Load Data
    • Connect with ADSDataset and ADSDatasetWithTarget
  • Label Data
    • Overview
    • Quick Start
    • Export Metadata
    • List
    • Load
    • Visualize
    • Examples
  • Transform Data
    • TextStrings
      • Overview
      • Quick Start
      • NLP Parse
      • Plugin
      • RegEx Match
      • Still a String
    • Text Extraction
  • Visualize Data
  • Train Models
    • ADSTuner
    • Training with OCI
    • Training Large Language Model
    • Distributed Training
      • Getting Started
      • Configurations
      • Developer Guide
      • Dask
        • Creating Workloads
        • Writing Dask Code
        • Distributed XGBoost & LightGBM
        • Securing with TLS
        • Dask Cluster Tuning
        • Dask dashboard
      • Horovod
        • Creating Horovod Workloads
        • Writing Distributed code with Horovod Framework
        • Monitoring Training
      • PyTorch Distributed
        • Creating PyTorch Distributed Workloads
      • Tensorflow
        • Creating Tensorflow Workloads
      • Run Source Code from Git or Object Storage
      • YAML Schema
      • Troubleshooting
    • TensorBoard
    • Model Evaluation
      • Quick Start
      • Binary Classification
      • Multinomial Classification
      • Regression
    • Oracle AutoMLx
      • Quick Start
  • Register, Manage, and Deploy Models
    • Large Language Model
    • Quick Start
    • Model Registration
    • Model Schema
    • Model Metadata
    • Customizing the Model
    • Model Version Set
    • Deploy Model with Conda Runtime
    • Deploy Model with Container Runtime
    • Upload a Model Group artifact (homogeneous)
    • Load Registered Model
    • SklearnModel
    • PyTorchModel
    • TensorFlowModel
    • SparkPipelineModel
    • LightGBMModel
    • XGBoostModel
    • HuggingFacePipelineModel
    • EmbeddingONNXModel
    • AutoMLModel
    • Other Frameworks

Integrations

  • Apache Spark
    • Quick Start
    • Setup and Installation
    • Running your Spark Application on OCI Data Flow
    • spark-defaults.conf
    • Data Catalog Metastore
      • Prerequisite
      • Quick Start
      • Data Flow
      • Interactive Spark
    • OCI Data Flow Studio
    • [Legacy]
  • Big Data Service
    • Quick Start
    • Conda Environment
    • Connect
    • File Management
    • SQL Data Management
  • Data Science Jobs
    • Quick Start
    • IAM Policies
    • Infrastructure and Runtime
    • Run a Python Workload
    • Run a Notebook
    • Run a Script
    • Run a Container
    • Run Code from Git Repo
    • Train PyTorch Models
    • Working with the CLI
    • Monitoring With CLI
    • Local Job Execution
    • YAML Schema
  • Data Science Pipelines
    • Overview
    • Quick Start
    • Pipeline
    • Pipeline Step
    • Pipeline Run
    • Examples
    • Local Pipeline Execution
  • Large Language Model
    • AI Quick Actions HTTP Client
    • Training Large Language Model
    • LangChain Integration
    • AutoGen Integration
    • LlamaIndex Integration
    • Deploy LLM Applications and Agents
    • Integration with OCI Generative AI and OpenSearch
    • Guardrails
  • Store Credentials
    • Quick Start
    • Auth Token
    • Autonomous Database
    • Big Data Service
    • MySQL
    • Oracle Database

Classes

  • Class Documentation
    • ads package
      • ads.aqua package
        • ads.aqua.common package
        • ads.aqua.model package
        • ads.aqua.modeldeployment package
        • ads.aqua.finetuning package
        • ads.aqua.evaluation package
      • ads.bds package
      • ads.catalog package
      • ads.common package
        • ads.common.artifact package
        • ads.common.decorator package
        • ads.common.function package
      • ads.data_labeling package
        • ads.data_labeling.interface package
        • ads.data_labeling.loader package
        • ads.data_labeling.mixin package
        • ads.data_labeling.parser package
        • ads.data_labeling.reader package
        • ads.data_labeling.visualizer package
      • ads.database package
      • ads.dataflow package
      • ads.dataset package
      • ads.dbmixin package
      • ads.environment package
      • ads.evaluations package
      • ads.experiments package
      • ads.explanations package
      • ads.feature_engineering package
        • ads.feature_engineering.accessor package
          • ads.feature_engineering.accessor.mixin package
        • ads.feature_engineering.adsimage package
          • ads.feature_engineering.adsimage.interface package
        • ads.feature_engineering.adsstring package
          • ads.feature_engineering.adsstring.oci_language package
          • ads.feature_engineering.adsstring.parsers package
          • ads.feature_engineering.adsstring.string package
        • ads.feature_engineering.dataset package
        • ads.feature_engineering.feature_type package
          • ads.feature_engineering.feature_type.adsstring package
            • ads.feature_engineering.feature_type.adsstring.parsers package
          • ads.feature_engineering.feature_type.handler package
      • ads.hpo package
        • ads.hpo.visualization package
      • ads.jobs package
        • ads.jobs.builders package
          • ads.jobs.builders.infrastructure package
          • ads.jobs.builders.runtimes package
        • ads.jobs.schema package
        • ads.jobs.templates package
      • ads.model package
        • ads.model.common package
        • ads.model.deployment package
          • ads.model.deployment.common package
        • ads.model.extractor package
        • ads.model.framework package
        • ads.model.model_artifact_boilerplate package
          • ads.model.model_artifact_boilerplate.artifact_introspection_test package
        • ads.model.runtime package
        • ads.model.service package
        • ads.model.transformer package
      • ads.model_artifact_boilerplate package
        • ads.model_artifact_boilerplate.artifact_introspection_test package
      • ads.mysqldb package
      • ads.opctl package
        • ads.opctl.backend package
        • ads.opctl.conda package
        • ads.opctl.config package
          • ads.opctl.config.diagnostics package
          • ads.opctl.config.yaml_parsers package
            • ads.opctl.config.yaml_parsers.distributed package
        • ads.opctl.diagnostics package
        • ads.opctl.distributed package
          • ads.opctl.distributed.common package
        • ads.opctl.spark package
      • ads.oracledb package
      • ads.pipeline package
        • ads.pipeline.builders package
          • ads.pipeline.builders.infrastructure package
        • ads.pipeline.schema package
        • ads.pipeline.visualizer package
      • ads.secrets package
      • ads.telemetry package
      • ads.text_dataset package
      • ads.type_discovery package
      • ads.vault package
Back to top
View this page

Model EvaluationΒΆ

  • Overview
  • Binary Classification
  • Multinomial Classification
Copyright © 2020, 2026 Oracle and/or its affiliates. Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
Made with Sphinx and @pradyunsg's Furo