Graviti Help Center
  • Graviti Help Center
  • Developer Documentation
    • Developer Tools
      • Graviti Python SDK
      • Graviti CLI
      • Graviti Open API
        • DataSet Operation
        • Data Operation
        • Examples
          • Model training
          • Data mining
  • Product Documentation
    • TensorBay
      • TensorBay: For All Stages of Algorithm Research
      • Quick Start for Developers
      • Quick Start for Team
      • How to Quickly Prepare a Dataset
        • How to Create a New Dataset
        • Manage Data in Cloud Storage
        • Create a Dataset by Filtering
        • Create a Dataset by Merging
        • Quick Use of Open Datasets by Forking
      • Version Control
        • Manage Data Files
        • Manage Annotations
        • Manage Dataset Information
        • Manage Versions
        • Manage Dataset Branches
        • Dataset Activities
        • Dataset Settings
      • Pharos Online Data Visualization
        • Explore Pharos
        • Pharos Visualization Widgets Instruction
      • Collaboration
        • Create a New Team
        • Invite Team Members
        • Team Management
        • Dataset Management
        • View Activity Log
      • How to Integrate TensorBay into Your Pipeline
      • Action
        • Create a Workflow
        • Run Workflows
        • Manage Workflows
        • YAML Syntax Description
        • Crontab syntax Description
        • Automatic Configurations
    • Open Datasets
      • Basic Concepts
      • Search for Datasets
      • Preview Data and Label Distribution Online
      • Use and Manage Datasets Online
      • Download Open Datasets
      • Didn't find the dataset you want?
  • APPs
    • GroundTruth Tools
      • Annotate pictures
    • Sextant
      • Create an Evaluation
      • Custom Metrics
      • Start to Evaluate
      • View Results
  • Release Note
  • Graviti Official Website
Powered by GitBook
On this page

Was this helpful?

  1. APPs
  2. Sextant

Create an Evaluation

PreviousSextantNextCustom Metrics

Last updated 3 years ago

Was this helpful?

  • Click Apps on the top navigation bar on the GAS page, and then click Sextant to enter to the page of Sextant.

  • Click New Evaluation on the upper right corner to enter the new page of the evaluation.

  • Fill in basic information and select benchmark data and the categories to be evaluated to complete the creation.

The required information for creating a new evaluation is as following:

1. Benchmark dataset

The benchmark dataset is used to evaluate the generated metrics as a reference, such as the ground truth data. (in common model evaluation scenarios)

Currently, only the TensorBay dataset can be chosen as the benchmark dataset. If you want to use data from local or other cloud storage, please upload the data to TensorBay first. For details, please check the following article.

2.Evaluated annotation types

The type of data annotation that needs to be evaluated. Currently, only Box2D is supported.

3. Evaluated categories

The categories of objects that need to be evaluated

4. IoU threshold

A preset IoU threshold. In evaluations, the IoU higher than the threshold is considered to be a hit; otherwise, it is considered to be a miss. Here you need to fill in a two-digit number between 0 and 1.

Currently, only one IoU threshold is supported to be added for a single evaluation. Please look forward to the coming of simultaneous evaluation with multiple thresholds and other related features.

How to Quickly Prepare a Dataset