Downloads · 30 days
18
20% of all-time downloads
yolo26n-coco128-finetune
deki/yolo26n-coco128-finetune
yolo26n-coco128-finetune is a object detection model from deki. Use it when you need objects located in an image. It is set up for ultralytics. The card lists the license as agpl-3.0.
This repository contains best.pt, a YOLO26n object-detection model fine-tuned on the COCO128 dataset.
All-time downloads
89
Public
Repo size
5.5 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt5.5 MB · 100%
At a glance
- Task
- Object Detection
- Library
- ultralytics
- License
- agpl-3.0
- Access
- Public
- Created
- Jul 1, 2026
- Updated
- Jul 1, 2026
- SHA
- d4f684d1
Datasets
Model card
From the Hugging Face model README
YOLO26n COCO128 Fine-Tuned Object Detection
This repository contains best.pt, a YOLO26n object-detection model fine-tuned on the COCO128 dataset.
Training
The model was initialized from pretrained YOLO26n weights and fine-tuned on COCO128 using Ultralytics.
Training settings:
- Base model:
yolo26n.pt - Dataset:
coco128.yaml - Epochs: 50
- Image size: 512
- Batch size: 4
- Device: Apple MPS
- Run name:
yolo26n_coco128_finetune_v2
Results
Best validation metrics from the training run:
- mAP50: 0.731
- mAP50-95: 0.558
Usage
from ultralytics import YOLO
model = YOLO("best.pt")
results = model("image.jpg")
results[0].show()
- Task
- Object Detection
- Library
- ultralytics
- License
- agpl-3.0
- Created
- Jul 1, 2026
- Updated
- Jul 1, 2026