Downloads · 30 days
0
fast-scnn-floor-segmentation
Tanishjain9/fast-scnn-floor-segmentation
fast-scnn-floor-segmentation is a machine learning model from Tanishjain9. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Lightweight Fast-SCNN model for indoor floor segmentation.
Access
Public
Updated Aug 8, 2026
Repo size
7.4 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth4.7 MB · 61%
At a glance
- Access
- Public
- Created
- Aug 8, 2026
- Updated
- Aug 8, 2026
- SHA
- 9c8e45dc
Model card
From the Hugging Face model README
Fast-SCNN Floor Segmentation
Lightweight Fast-SCNN model for indoor floor segmentation.
- Task: Semantic Segmentation
- Class: Floor
- Input: RGB
512×512 - Pixel Accuracy: 94.9%
- mIoU: 87.8%
Model Formats
- PyTorch:
.pth - ONNX:
.onnx - OpenVINO:
.xml + .bin
Performance
OpenVINO FP32: 26.02 FPS / 38.44 ms per frame on Intel Core 7 240H.
Limitations
Designed for indoor floor segmentation. Performance may degrade with unseen environments, lighting changes, shadows, furniture, and floor-like surfaces.
The model detects floor only and does not perform obstacle detection.
- Created
- Aug 8, 2026
- Updated
- Aug 8, 2026