You can deploy this model and start earning money today!

Mrumairahmad100/
renovision-yolo

Name: renovision-yolo
Availability: InStock

Views

No views yet

RenoVision — YOLOv8m Interior Object Detection

Custom YOLOv8m model trained on HomeObjects-3K dataset for interior room object detection in the RenoVision AI Interior Renovation Planner.

Project: RenoVision — AI-Powered Smart Interior Planner University: Lahore Garrison University — BSCS 2024 Authors: Ahmad Raza & Tabeel John

Performance

Metric	Value
mAP@50	0.7358
mAP@50-95	0.5381
Precision	0.7482
Recall	0.6811
Train Images	2285
Val Images	404

Classes (12 Interior Objects)

ID	Class
0	bed
1	sofa
2	chair
3	table
4	lamp
5	tv
6	laptop
7	wardrobe
8	window
9	door
10	potted plant
11	photo frame

Dataset

HomeObjects-3K by Ultralytics — 3,000 annotated indoor home images https://docs.ultralytics.com/datasets/detect/homeobjects-3k

Training

Base: YOLOv8m pretrained on COCO
Epochs: 100 (early stopping, patience=20)
Image size: 640×640 | Batch: 16 | Optimizer: AdamW
Augmentation: Mosaic, MixUp, HSV, Flip, Copy-Paste

Usage

python

from ultralytics import YOLO

model   = YOLO('best.pt')
results = model('room_photo.jpg', conf=0.25)

CLASS_NAMES = ['bed', 'sofa', 'chair', 'table', 'lamp', 'tv', 'laptop', 'wardrobe', 'window', 'door', 'potted plant', 'photo frame']
for box in results[0].boxes:
    name = CLASS_NAMES[int(box.cls[0])]
    conf = float(box.conf[0])
    print(f'{name}: {conf:.2f}')

Mrumairahmad100/renovision-yolo