Spaces:
Running
Download README.md from dzakybd/quantity-lab: direct link, hf CLI and curl.
- Browser
- Download file 1.38 kB
-
https://huggingface.co/spaces/dzakybd/quantity-lab/resolve/main/README.md
- Command line
-
hf download hf://spaces/dzakybd/quantity-lab/README.md
-
curl -L -o README.md https://huggingface.co/spaces/dzakybd/quantity-lab/resolve/main/README.md
title: quantity-lab
emoji: ๐
colorFrom: indigo
colorTo: gray
sdk: static
pinned: false
license: mit
short_description: How small floor-plan errors distort area and room counts
quantity-lab showcase
A number written on a drawing is a claim, not a takeoff: an earlier hand takeoff, often partial, stale on revision. The per-room finishing quantities that drive a price โ tile from the floor polygon, skirting from its perimeter, paint from wall area โ are computed from the room polygon. So the polygon is what has to be right.
How small geometry errors turn into wrong takeoff quantities. Pick a synthetic floor plan and a mode: the annotated rooms (oracle), a controlled error (rooms 2 or 5 px too small or too big, a missing divider, a spurious line), a classical OpenCV room baseline, or the pretrained CubiCasa5K segmentation model (its output on synthetic plans, computed ahead of time). The tables give measured results on ten held-out CubiCasa5K test plans, as numbers only. Everything was computed ahead of time; the page runs no model.
Code (MIT): github.com/dzakybd/quantity-lab. Write-up: dzaky.ai.id.
CubiCasa5K: Kalervo et al., SCIA 2019, https://zenodo.org/records/2613548 (CC BY-NC-SA 4.0). No CubiCasa5K image is included in this Space.