Downloads · 30 days
0
cracker-yolo26l-baseline
Mezosky/cracker-yolo26l-baseline
cracker-yolo26l-baseline is a machine learning model from Mezosky. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository stores trained crack-detection weights for Mezosky/cracker-yolo26l-baseline.
Access
Public
Updated Mar 17, 2026
Repo size
107 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt106 MB · 99%
At a glance
- Access
- Public
- Created
- Mar 17, 2026
- Updated
- Mar 17, 2026
- SHA
- 188acce8
Model card
From the Hugging Face model README
Crack Detection YOLO26 Model
This repository stores trained crack-detection weights for Mezosky/cracker-yolo26l-baseline.
Files
best.ptartifacts/contains training curves and metadata (if available).
Training Run
- Source run directory:
runs/train/cracker_yolo26l_baseline
Final Validation Metrics
| Metric | Value |
|---|---|
| Precision | 0.7172 |
| Recall | 0.6615 |
| mAP50 | 0.6941 |
| mAP50-95 | 0.4074 |
Usage
from ultralytics import YOLO
model = YOLO('best.pt')
results = model.predict(source='image.jpg', conf=0.25)
- Created
- Mar 17, 2026
- Updated
- Mar 17, 2026