food-detector-yolo11n-smoke

Food Detector — YOLO11n

Overview

Single-class object detection model that detects food items in images and returns bounding box coordinates. Trained on the zhiyingzou0202/object_detection_bbox_merged_coco_food dataset (37,639 training images).

Model

• Architecture: YOLO11n (nano)
• Parameters: 2.6M
• Input size: 640x640
• Classes: 1 (food)
• Format: PyTorch + ONNX

Validation Metrics

Files

Usage

Python (PyTorch)

from ultralytics import YOLO

model = YOLO("best.pt")
results = model("path/to/image.jpg")

for result in results:
    boxes = result.boxes
    for box in boxes:
        x1, y1, x2, y2 = box.xyxy[0].tolist()
        conf = box.conf[0].item()
        print(f"Food detected: bbox=({x1:.0f}, {y1:.0f}, {x2:.0f}, {y2:.0f}), confidence={conf:.2f}")

Browser (ONNX Runtime Web)

import * as ort from "onnxruntime-web";

const session = await ort.InferenceSession.create("best_static.onnx");
// Preprocess image to 640x640, normalize, create NCHW tensor
// Run inference, apply NMS, draw bounding boxes

Training Configuration

• Epochs: 2
• Image size: 640
• Batch size: 16
• Optimizer: auto (AdamW)
• Learning rate: 0.01 -> 0.0001 (cosine)
• Transfer learning from COCO-pretrained YOLO11n

<!-- ml-intern-provenance -->

Generated by ML Intern

This model repository was generated by ML Intern, an agent for machine learning research and development on the Hugging Face Hub.

• Try ML Intern: https://smolagents-ml-intern.hf.space
• Source code: https://github.com/huggingface/ml-intern