Skip to main content

Shared taxonomy definitions for computer vision inspection domains

Project description

dyslexai-taxonomy

Shared taxonomy definitions for computer vision inspection domains.

Overview

This package provides standardized category definitions, compliance rules, and calibration data for computer vision models targeting inspection domains. Both data generation tools (kubric-stair) and runtime inference applications (spatial-vision-app) import from this shared taxonomy.

Installation

pip install dyslexai-taxonomy

For development:

pip install -e ".[dev]"

Usage

from dyslexai_taxonomy import get_domain, list_domains

# List available domains
domains = list_domains()
# ['spatial_vision']

# Get a specific domain
domain = get_domain("spatial_vision")

# Access categories
coarse = domain.get_coarse_categories()
fine = domain.get_fine_categories()

# Get compliance rules for a category
rules = domain.get_compliance_rules("outlet")

Direct imports

from dyslexai_taxonomy.domains.spatial_vision import (
    COARSE_CATEGORIES,
    FINE_CATEGORIES,
    get_coarse_for_fine,
    get_compliance_rules,
    CALIBRATION_ANCHORS,
)

# Get parent category for a fine category
coarse = get_coarse_for_fine("gfci")  # Returns "outlet"

# Get standard dimensions for calibration
outlet_dims = CALIBRATION_ANCHORS["outlet"]

Architecture

dyslexai-taxonomy (standalone)
       ↑                    ↑
       │                    │
kubric-stair          spatial-vision-app
(data generation)     (runtime inference)

Both projects import from dyslexai-taxonomy independently. Neither depends on the other.

Domains

spatial_vision

Home inspection and code compliance domain.

Coarse Categories (15-18):

  • Wall components: outlet, switch, vent, panel, thermostat, junction_box
  • Openings: door, window, cabinet_door
  • Vertical transport: stair, ramp
  • HVAC equipment: furnace, water_heater, ac_unit
  • Safety: smoke_detector, co_detector
  • Background: wall_surface, floor_surface

Fine Categories (150+): Each coarse category expands to multiple fine subcategories. For example:

  • outlet → duplex, gfci, usb, 240v, outdoor...
  • stair → straight, l_shaped, spiral, exterior...

Compliance Rules:

  • NEC (National Electrical Code)
  • IRC (International Residential Code)
  • ADA (Americans with Disabilities Act)
  • NFPA (Fire safety)

License

Apache-2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dyslexai_taxonomy-0.1.0.tar.gz (19.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

dyslexai_taxonomy-0.1.0-py3-none-any.whl (22.4 kB view details)

Uploaded Python 3

File details

Details for the file dyslexai_taxonomy-0.1.0.tar.gz.

File metadata

  • Download URL: dyslexai_taxonomy-0.1.0.tar.gz
  • Upload date:
  • Size: 19.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for dyslexai_taxonomy-0.1.0.tar.gz
Algorithm Hash digest
SHA256 9bed955713862101c3a76a0650f956910adce6af9518c23096649159cfdef767
MD5 39047180761379bee97202a335ba7f05
BLAKE2b-256 1357766e7f002ad6d71d9e5f1f1fb9bef4cad82aaed844270238c9b3c6a85df6

See more details on using hashes here.

File details

Details for the file dyslexai_taxonomy-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for dyslexai_taxonomy-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0d3613eddff393a3f2e8714d6955d62998e3e3231da4eee24cf24cef577fc59e
MD5 6ea37c77a040efea2559871ba253a75c
BLAKE2b-256 99018fc6dccc2e15c4bef596bf774602ca5be577644cd2b54866b30f813a48d1

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page