Open Source Ecosystems

notebooks | inference | autodistill | maestro

👋 hello

We write your reusable computer vision tools. Whether you need to load your dataset from your hard drive, draw detections on an image or video, or count how many detections are in a zone. You can count on us! 🤝

💻 install

Pip install the supervision package in a Python>=3.8 environment.

pip install supervision

Read more about conda, mamba, and installing from source in our guide.

🔥 quickstart

models

Supervision was designed to be model agnostic. Just plug in any classification, detection, or segmentation model. For your convenience, we have created connectors for the most popular libraries like Ultralytics, Transformers, or MMDetection.

import cv2
import supervision as sv
from ultralytics import YOLO

image = cv2.imread(...)
model = YOLO("yolov8s.pt")
result = model(image)[0]
detections = sv.Detections.from_ultralytics(result)

len(detections)
# 5

inference

Running with Inference requires a Roboflow API KEY.

import cv2
import supervision as sv
from inference import get_model

image = cv2.imread(...)
model = get_model(model_id="yolov8s-640", api_key=<ROBOFLOW API KEY>)
result = model.infer(image)[0]
detections = sv.Detections.from_inference(result)

len(detections)
# 5

annotators

Supervision offers a wide range of highly customizable annotators, allowing you to compose the perfect visualization for your use case.

import cv2
import supervision as sv

image = cv2.imread(...)
detections = sv.Detections(...)

box_annotator = sv.BoxAnnotator()
annotated_frame = box_annotator.annotate(
  scene=image.copy(),
  detections=detections)

https://github.com/roboflow/supervision/assets/26109316/691e219c-0565-4403-9218-ab5644f39bce

datasets

Supervision provides a set of utils that allow you to load, split, merge, and save datasets in one of the supported formats.

import supervision as sv
from roboflow import Roboflow

project = Roboflow().workspace(<WORKSPACE_ID>).project(<PROJECT_ID>)
dataset = project.version(<PROJECT_VERSION>).download("coco")

ds = sv.DetectionDataset.from_coco(
    images_directory_path=f"{dataset.location}/train",
    annotations_path=f"{dataset.location}/train/_annotations.coco.json",
)

path, image, annotation = ds[0]
    # loads image on demand

for path, image, annotation in ds:
    # loads image on demand

load

dataset = sv.DetectionDataset.from_yolo(
    images_directory_path=...,
    annotations_directory_path=...,
    data_yaml_path=...
)

dataset = sv.DetectionDataset.from_pascal_voc(
    images_directory_path=...,
    annotations_directory_path=...
)

dataset = sv.DetectionDataset.from_coco(
    images_directory_path=...,
    annotations_path=...
)

split

train_dataset, test_dataset = dataset.split(split_ratio=0.7)
test_dataset, valid_dataset = test_dataset.split(split_ratio=0.5)

len(train_dataset), len(test_dataset), len(valid_dataset)
# (700, 150, 150)

merge

ds_1 = sv.DetectionDataset(...)
len(ds_1)
# 100
ds_1.classes
# ['dog', 'person']

ds_2 = sv.DetectionDataset(...)
len(ds_2)
# 200
ds_2.classes
# ['cat']

ds_merged = sv.DetectionDataset.merge([ds_1, ds_2])
len(ds_merged)
# 300
ds_merged.classes
# ['cat', 'dog', 'person']

save

dataset.as_yolo(
    images_directory_path=...,
    annotations_directory_path=...,
    data_yaml_path=...
)

dataset.as_pascal_voc(
    images_directory_path=...,
    annotations_directory_path=...
)

dataset.as_coco(
    images_directory_path=...,
    annotations_path=...
)

convert

sv.DetectionDataset.from_yolo(
    images_directory_path=...,
    annotations_directory_path=...,
    data_yaml_path=...
).as_pascal_voc(
    images_directory_path=...,
    annotations_directory_path=...
)