Yolo-World module for use with Autodistill
Project description
Autodistill: YOLO-World Base Model
This repository contains the code implementing YOLO-World as a Base Model for use with autodistill
.
YOLO-World combines YOLO-World brings YOLO like efficiency for training and inferring open-vocabulary models
Read the full Autodistill documentation.
Installation
To use the YOLO-World, simply install it along with a Target Model supporting the detection
task:
pip3 install autodistill-yolo-world
You can find a full list of detection
Target Models on the main autodistill repo.
Quickstart
from autodistill_yolo_world import YoloWorld
from autodistill.detection import CaptionOntology
from autodistill.utils import plot
import cv2
# define an ontology to map class names to our GroundedSAM prompt
# the ontology dictionary has the format {caption: class}
# where caption is the prompt sent to the base model, and class is the label that will
# be saved for that caption in the generated annotations
# then, load the model
base_model = YoloWorld(
ontology=CaptionOntology(
{
"person": "person",
"car": "car",
}
),
model_type = "yolov8s-world.pt"
)
# run inference on a single image
results = base_model.predict("assets/test.jpg")
plot(
image=cv2.imread("assets/test.jpg"),
classes=base_model.ontology.classes(),
detections=results
)
# label all images in a folder called `context_images`
base_model.label("./context_images", extension=".jpeg")
License
The code in this repository is licensed under an Apache 2.0 license.
🏆 Thanks
Thanks to autodistill and ultralytics
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for autodistill_yolo_world-0.1.0.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | e54096142b0a03fc2eb3ad2f0892f9356868f29c26cf0e8b6c880367e9bede9c |
|
MD5 | 10c900189274a96c3a88a9a23e27e0a8 |
|
BLAKE2b-256 | e05fdcd8c90cdccabba436f33ecc7f3e3d94b9d6ef97e36c6dbe364c5df8222c |
Close
Hashes for autodistill_yolo_world-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 72ec153ba7675a2967b191269b74063eaadc84ae338abe443046d997b40db646 |
|
MD5 | acd5f344cb425584610b94c84ce03251 |
|
BLAKE2b-256 | 9f5ce4337a53d4c1706a92a617ab7f6069bfd5451f9dc832efc581385ca13e58 |