rujutashashikanjoshi/yolo12-vehicle_detection-4139_full_v2.1-100m

YOLOv12 MEDIUM Model

Fine-tuned YOLOv12 model for object detection.

Model Details

• Architecture: YOLOv12Medium
• Framework: Ultralytics YOLOv12
• Resolution: 640x640
• Epochs: 100
• Batch Size: 16

Classes

car

Usage

from ultralytics import YOLO
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="rujutashashikanjoshi/yolo12-vehicle_detection-4139_full_v2.1-100m", filename="best.pt")
model = YOLO(model_path)

results = model("your_image.jpg", conf=0.25)
results[0].show()

Training Config

{
    "model_type": "medium",
    "epochs": 100,
    "batch_size": 16,
    "image_size": 640,
    "learning_rate": 0.01,
    "weight_decay": 0.0005,
    "momentum": 0.937,
    "warmup_epochs": 3,
    "workers": 4,
    "patience": 30,
    "save_period": 10,
    "conf_threshold": 0.25,
    "iou_threshold": 0.45,
    "output_dir": "./output/4139_fullv2.1"
}

License

AGPL-3.0