YOLOlite

YOLOlite is a lightweight object detection model family from Roboflow, designed for low-latency deployments and edge hardware. You can train YOLOlite on a Project in Roboflow and deploy it via our Serverless Cloud API.

For self-hosted deployment, see Roboflow Inference.

YOLOlite input size is configured during training on Roboflow.

YOLOlite available variants

YOLOlite ships in two scaling families: a standard set and an edge-optimized set. Each is available in five sizes.

You select a variant when you start a training on a Project. The trained model is then served from the Serverless Cloud API, where you call it by its per-model {workspace}/{model-slug} ID (see Versions, Trainings, and Models).

YOLOlite API

1

Get your API Key

Create a Roboflow account, find your key on the Roboflow API settings page and make it available to your shell:

Copy

export ROBOFLOW_API_KEY="your-key-here"

2

Install the dependencies

Install the Inference SDK and supervision:

Copy

pip install -U inference-sdk supervision

3

Run the model

This example runs a public YOLOlite model trained on a screws dataset (screw, flat-washer, hex-nut). Swap in your own {workspace}/{model-slug} to run your trained weights.

Copy

import os
import cv2
import supervision as sv
from inference_sdk import InferenceHTTPClient

image = sv.load_image_from_url("https://media.roboflow.com/docs/bolts.jpg")

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.environ["ROBOFLOW_API_KEY"],
)
results = client.infer(image, model_id="erik-pe6au/rf-bolts-4-yololite-s-t1")

detections = sv.Detections.from_inference(results)

annotated = sv.BoxAnnotator().annotate(image.copy(), detections)

cv2.imwrite("annotated.png", annotated)