sadakvision-weights

devyansh99/sadakvision-weights

sadakvision-weights is a object detection model from devyansh99. Use it when you need objects located in an image. The card lists the license as mit.

Trained weights for Indian road defect + garbage detection (crack / garbage / manhole / pothole).

Downloads · 30 days

Access

Public

Updated Sep 22, 2026

Repo size

287 MB

Likes

Public

Repo makeup

Click a slice to open those files.

.pt154 MB · 53%

From the Hugging Face model README

Trained weights for Indian road defect + garbage detection (crack / garbage / manhole / pothole).

Dataset: Merged_Final_Data (Roboflow) — YOLO format, train/valid/test.

File	Source	Size
`yolov8m_100e_best.pt`	`yolov8m_res_100/train/weights/best.pt`	49.6 MB
`yolov8m_runs_best.pt`	`yolov8m_runs/pothole_yolov8m/weights/best.pt`	49.6 MB
`yolo26m_best.pt`	`yolo26_results/yolo26m_runs/weights/best.pt`	42 MB
`yolov11n_best.pt`	`yolov11n_res/runs_yolov11n/weights/best.pt`	5.2 MB
`rfdetr_best.pth`	`rfdetr/checkpoint_best_total.pth`	127.6 MB

Model	mAP50	mAP50-95	Precision	Recall
YOLOv8m (100e, imgsz 640, batch 32)	0.773	0.489	0.858	0.736
YOLOv26m (100e, batch 16)	0.757	0.386	0.824	0.737
YOLOv11n (100e, imgsz 512, batch 64)	0.633	0.294	0.721	0.594
RF-DETR (medium)	0.796	0.550	0.881	0.768

RF-DETR val also: F1 0.817, mAP75 0.586, mAR 0.660. Per-class AP: crack 0.730, manhole 0.686, pothole 0.525, garbage 0.259 — garbage hardest.

Test: YOLOv8m mAP50 0.742, YOLOv26m 0.741, YOLOv11n 0.644.

pip install ultralytics
yolo detect predict model=yolov8m_100e_best.pt source=your_image.jpg save=True

RF-DETR .pth is the checkpoint_best_total.pth (no optimizer state).