Dataiku Documentation
  • Discussions
    • Setup & Configuration
    • Using Dataiku DSS
    • Plugins & Extending Dataiku DSS
    • General Discussion
    • Job Board
    • Community Resources
    • Product Ideas
  • Knowledge
    • Getting Started
    • Knowledge Base
    • Reference Documentation
    • Developer Guide
  • Academy
    • Quick Start Programs
    • Learning Paths
    • Certifications
    • Course Catalog
    • Academy Discussions
  • Community Programs
    • Upcoming User Events
    • Find a User Group
    • Past Events
    • Community Conundrums
    • Dataiku Neurons
    • Banana Data Podcast
  • What's New
  • User's Guide
  • DSS concepts
  • Connecting to data
  • Exploring your data
  • Schemas, storage types and meanings
  • Data preparation
  • Charts
  • Interactive statistics
  • Machine learning
    • Prediction (Supervised ML)
    • Clustering (Unsupervised ML)
    • Automated machine learning
    • Model Settings Reusability
    • Features handling
    • Algorithms reference
    • Advanced models optimization
    • Models ensembling
    • Model Document Generator
    • Time Series Forecasting
    • Deep Learning
    • Models lifecycle
    • Scoring engines
    • Writing custom models
    • Exporting models
    • Partitioned Models
    • ML Diagnostics
    • ML Assertions
    • Computer vision
      • Introduction
      • Computer vision analysis inputs
      • Your first Computer vision model
      • Model architectures & training parameters
      • Evaluation Metrics
      • Data augmentation
      • GPU support
      • Performance assessment
      • Endpoint APIs
    • Image labeling
  • The Flow
  • Visual recipes
  • Recipes based on code
  • Code notebooks
  • MLOps
  • Webapps
  • Code Studios
  • Code reports
  • Dashboards
  • Workspaces
  • Dataiku Applications
  • Working with partitions
  • DSS and SQL
  • DSS and Python
  • DSS and R
  • DSS and Spark
  • Code environments
  • Collaboration
  • Specific Data Processing
  • Time Series
  • Geographic data
  • Text
  • Images
  • Audio
  • Video
  • Automation & Deployment
  • Automation scenarios, metrics, and checks
  • Production deployments and bundles
  • API Node & API Deployer: Real-time APIs
  • Governance
  • APIs
  • Python APIs
  • R API
  • Public REST API
  • Additional APIs
  • Installation & Administration
  • Installing and setting up
  • Elastic AI computation
  • DSS in the cloud
  • DSS and Hadoop
  • Metastore catalog
  • Operating DSS
  • Security
  • User Isolation
  • Other topics
  • Plugins
  • Streaming data
  • Formula language
  • Custom variables expansion
  • Sampling methods
  • Accessibility
  • Troubleshooting
  • Release notes
  • Other Documentation
  • Third-party acknowledgements
  • Hive RCFile
  • MapR
  • Hive SequenceFile
  • Guided setup 2: Use an existing VPC
  • Impute with computed value
  • Columns selection
  • Mitigation for PwnKit (CVE-2021-4034)
  • Incorrect access control allows users to edit discussions
  • Ability to tamper with creation and ownership metadata
  • Directory traversal vulnerability in Shapefile parser
  • Incorrect access control in Jupyter notebooks
  • Stored XSS in object titles
  • Stored XSS in object titles
  • Access control issue on downloading project exports
  • Access control issue on changing dataset connections
  • Access control issue on dashboards listing
  • Access control issue on saving project permissions
  • PwnKit Linux vulnerability (CVE-2021-4034)
  • Access control issue on foreign managed folders
  • Cross-script-scripting on model reports
  • Code execution through server-side-template-injection
  • Insufficient access control on managed cluster logs and configuration
  • Multiple access control issues
  • Multiple access control issues
  • Stored XSS in dataset settings
  • Stored XSS in machine learning results
  • Insufficient access control on export to dataset
  • Remote code execution in API designer
  • Session credential disclosure
  • Insufficient access control to project variables
  • Insufficient access control to projects list and information
  • Insufficient access control in troubleshooting tools
  • Credentials disclosure through path traversal
  • Cross-site-scripting through custom metric names
  • Cross-site-scripting through imported Jupyter notebooks
  • Host blacklist bypass
  • Takeover of Jupyter notebooks
  • Missing authentication on internal API call
  • Cross-site-scripting through Jupyter notebooks
  • Race condition on UIF can lead to account takeover
  • Compatibility of DSS with CIS Benchmark Level 1 on RHEL/CentOS
  • Third-party acknowledgements (internal usage)
  • Unstructured data
Dataiku DSS
You are viewing the documentation for version 11 of DSS.
  • »
  • Machine learning »
  • Computer vision

Computer visionΒΆ

  • Introduction
  • Computer vision analysis inputs
    • Target column format for Object detection
    • Target column format for Image classification
    • Image path column
    • Supported images formats
  • Your first Computer vision model
    • Install the required packages
    • Create the analysis
    • Review the design of your model (optional)
    • Monitor the performance of your model during training
  • Model architectures & training parameters
    • Pre-trained models available
    • Training parameters
  • Evaluation Metrics
  • Data augmentation
    • Data augmentations settings
    • N.b. Object detection
  • GPU support
    • Selection of GPU
    • Using multi-GPU training
    • Requirements
  • Performance assessment
    • Object detection
      • Confusion matrix and image feed
      • Metrics
      • Precision-Recall curve
      • What if : Scoring new images on the go
    • Image classification
      • Confusion matrix and image feed
      • Metrics
      • Calibration curve, ROC curve & density charts
      • What if : Scoring new images on the go
  • Endpoint APIs
    • Input format
Next Previous

© Copyright 2022, Dataiku

Built with Sphinx using a theme provided by Read the Docs.