更新日志¶

import numpy as np
import supervision as sv
from ultralytics import YOLO

model = YOLO("yolov8m-pose.pt")
tracker = sv.ByteTrack()
trace_annotator = sv.TraceAnnotator()

def callback(frame: np.ndarray, _: int) -> np.ndarray:
    results = model(frame)[0]
    key_points = sv.KeyPoints.from_ultralytics(results)

    detections = key_points.as_detections()
    detections = tracker.update_with_detections(detections)

    annotated_image = trace_annotator.annotate(frame.copy(), detections)
    return annotated_image

sv.process_video(
    source_path="input_video.mp4",
    target_path="output_video.mp4",
    callback=callback
)

from supervision.assets import download_assets, VideoAssets

path_to_video = download_assets(VideoAssets.SKIING)

import supervision as sv
from supervision.metrics import MeanAverageRecall

predictions = sv.Detections(...)
targets = sv.Detections(...)

map_metric = MeanAverageRecall()
map_result = map_metric.update(predictions, targets).compute()

map_result.plot()

import supervision as sv
from supervision.metrics import Recall

predictions = sv.Detections(...)
targets = sv.Detections(...)

recall_metric = Recall()
recall_result = recall_metric.update(predictions, targets).compute()

recall_result.plot()

import supervision as sv
from supervision.metrics import F1_Score

predictions = sv.Detections(...)
targets = sv.Detections(...)

f1_metric = MeanAverageRecall(metric_target=sv.MetricTarget.ORIENTED_BOUNDING_BOXES)
f1_result = f1_metric.update(predictions, targets).compute()

import supervision as sv
from ultralytics import YOLO

image = cv2.imread("image.jpg")

label_annotator = sv.LabelAnnotator(smart_position=True)

model = YOLO("yolo11m.pt")
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)

annotated_frame = label_annotator.annotate(first_frame.copy(), detections)
sv.plot_image(annotated_frame)

import supervision as sv
from ultralytics import YOLO

model = YOLO("yolov8m")

result = model("image.png")[0]
detections = sv.Detections.from_ultralytics(result)

# Items in `data` must match length of detections
object_ids = [num for num in range(len(detections))]
detections.data["object_number"] = object_ids

# Items in `metadata` can be of any length.
detections.metadata["camera_model"] = "Luxonis OAK-D"

import supervision as sv
from supervision.metrics import F1Score

predictions = sv.Detections(...)
targets = sv.Detections(...)

f1_metric = F1Score()
f1_result = f1_metric.update(predictions, targets).compute()

print(f1_result)
print(f1_result.f1_50)
print(f1_result.small_objects.f1_50)

import supervision as sv
import cv2

image = cv2.imread("<SOURCE_IMAGE_PATH>")

line_zone = sv.LineZone(
    start=sv.Point(0, 100),
    end=sv.Point(50, 200)
)
line_zone_annotator = sv.LineZoneAnnotator(
    text_orient_to_line=True,
    display_text_box=False,
    text_centered=False
)

annotated_frame = line_zone_annotator.annotate(
    frame=image.copy(), line_counter=line_zone
)

sv.plot_image(frame)

import supervision as sv
import cv2

image = cv2.imread("<SOURCE_IMAGE_PATH>")

line_zone = sv.LineZone(
    start=sv.Point(0, 100),
    end=sv.Point(50, 200)
)
line_zone_annotator = sv.LineZoneAnnotatorMulticlass()

frame = line_zone_annotator.annotate(
    frame=frame, line_zones=[line_zone]
)

sv.plot_image(frame)

import supervision as sv
import easyocr
import cv2

image = cv2.imread("<SOURCE_IMAGE_PATH>")

reader = easyocr.Reader(["en"])
result = reader.readtext("<SOURCE_IMAGE_PATH>", paragraph=True)
detections = sv.Detections.from_easyocr(result)

box_annotator = sv.BoxAnnotator(color_lookup=sv.ColorLookup.INDEX)
label_annotator = sv.LabelAnnotator(color_lookup=sv.ColorLookup.INDEX)

annotated_image = image.copy()
annotated_image = box_annotator.annotate(scene=annotated_image, detections=detections)
annotated_image = label_annotator.annotate(scene=annotated_image, detections=detections)

sv.plot_image(annotated_image)

import numpy as np

boxes_true = np.array([[[1, 0], [0, 1], [3, 4], [4, 3]]])
boxes_detection = np.array([[[1, 1], [2, 0], [4, 2], [3, 3]]])
ious = sv.oriented_box_iou_batch(boxes_true, boxes_detection)
print("IoU between true and detected boxes:", ious)

import cv2
from ncnn.model_zoo import get_model
import supervision as sv

image = cv2.imread("<SOURCE_IMAGE_PATH>")
model = get_model(
    "yolov8s",
    target_size=640,
    prob_threshold=0.5,
    nms_threshold=0.45,
    num_threads=4,
    use_gpu=True,
)
result = model(image)
detections = sv.Detections.from_ncnn(result)

import supervision as sv
from inference import get_model

image = <SOURCE_IMAGE_PATH>
icon_dog = <DOG_PNG_PATH>
icon_cat = <CAT_PNG_PATH>

model = get_model(model_id="yolov8n-640")
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)

icon_paths = []
for class_name in detections.data["class_name"]:
    if class_name == "dog":
        icon_paths.append(icon_dog)
    elif class_name == "cat":
        icon_paths.append(icon_cat)
    else:
        icon_paths.append("")

icon_annotator = sv.IconAnnotator()
annotated_frame = icon_annotator.annotate(
    scene=image.copy(),
    detections=detections,
    icon_path=icon_paths
)

import supervision as sv
from inference import get_model

image = <SOURCE_IMAGE_PATH>

model = get_model(model_id="yolov8n-640")
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)

background_overlay_annotator = sv.BackgroundOverlayAnnotator()
annotated_frame = background_overlay_annotator.annotate(
    scene=image.copy(),
    detections=detections
)

import torch
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection

processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")

image = Image.open(<SOURCE_IMAGE_PATH>)
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)

width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_object_detection(
    outputs=outputs, target_sizes=target_size)[0]
detections = sv.Detections.from_transformers(
    transformers_results=results,
    id2label=model.config.id2label)

import supervision as sv
from segment_anything import (
    sam_model_registry,
    SamAutomaticMaskGenerator
)
sam_model_reg = sam_model_registry[MODEL_TYPE]
sam = sam_model_reg(checkpoint=CHECKPOINT_PATH).to(device=DEVICE)
mask_generator = SamAutomaticMaskGenerator(sam)
sam_result = mask_generator.generate(IMAGE)
detections = sv.Detections.from_sam(sam_result=sam_result)

import supervision as sv

for frame in sv.get_video_frames_generator(
    source_path=<SOURCE_VIDEO_PATH>,
    start=60,
    iterative_seek=True
):
    ...

import roboflow
from roboflow import Roboflow
import supervision as sv

roboflow.login()
rf = Roboflow()

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

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

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

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

import supervision as sv
from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
import cv2

image = cv2.imread(<SOURCE_IMAGE_PATH>)
cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")
predictor = DefaultPredictor(cfg)

result = predictor(image)
detections = sv.Detections.from_detectron2(result)

mask_annotator = sv.MaskAnnotator()
annotated_frame = mask_annotator.annotate(scene=image.copy(), detections=detections)

import cv2
import supervision as sv
import

image = cv2.imread(<SOURCE_IMAGE_PATH>)

model = get_model(model_id="yolov8n-640")
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)

rich_label_annotator = sv.RichLabelAnnotator(font_path=<TTF_FONT_PATH>)
annotated_image = rich_label_annotator.annotate(scene=image.copy(), detections=detections)

import supervision as sv

train_ds = sv.DetectionDataset.from_yolo(
    images_directory_path="/content/dataset/train/images",
    annotations_directory_path="/content/dataset/train/labels",
    data_yaml_path="/content/dataset/data.yaml",
    is_obb=True,
)

_, image, detections in train_ds[0]

obb_annotator = OrientedBoxAnnotator()
annotated_image = obb_annotator.annotate(scene=image.copy(), detections=detections)

import supervision as sv

paligemma_result = "<loc0256><loc0256><loc0768><loc0768> cat"
detections = sv.Detections.from_lmm(
    sv.LMM.PALIGEMMA,
    paligemma_result,
    resolution_wh=(1000, 1000),
    classes=["cat", "dog"],
)
detections.xyxy
# array([[250., 250., 750., 750.]])

detections.class_id
# array([0])

import supervision as sv

image = ...
key_points = sv.KeyPoints(...)

edge_annotator = sv.EdgeAnnotator(
    color=sv.Color.GREEN,
    thickness=5
)
annotated_frame = edge_annotator.annotate(
    scene=image.copy(),
    key_points=key_points
)

import cv2
import numpy as np
import supervision as sv
from inference import get_model

model = get_model(model_id="yolov8x-seg-640")
image = cv2.imread(<SOURCE_IMAGE_PATH>)

def callback(image_slice: np.ndarray) -> sv.Detections:
    results = model.infer(image_slice)[0]
    return sv.Detections.from_inference(results)

slicer = sv.InferenceSlicer(callback = callback)
detections = slicer(image)

mask_annotator = sv.MaskAnnotator()
label_annotator = sv.LabelAnnotator()

annotated_image = mask_annotator.annotate(
    scene=image, detections=detections)
annotated_image = label_annotator.annotate(
    scene=annotated_image, detections=detections)

import cv2
import supervision as sv
from ultralytics import YOLO

image = cv2.imread(<SOURCE_IMAGE_PATH>)
model = YOLO('yolov8l-pose')

result = model(image, verbose=False)[0]
keypoints = sv.KeyPoints.from_ultralytics(result)

edge_annotators = sv.EdgeAnnotator(color=sv.Color.GREEN, thickness=5)
annotated_image = edge_annotators.annotate(image.copy(), keypoints)

import torch
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForSegmentation

processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50-panoptic")
model = DetrForSegmentation.from_pretrained("facebook/detr-resnet-50-panoptic")

image = Image.open(<SOURCE_IMAGE_PATH>)
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)

width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_segmentation(
    outputs=outputs, target_sizes=target_size)[0]
detections = sv.Detections.from_transformers(results, id2label=model.config.id2label)

mask_annotator = sv.MaskAnnotator()
label_annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER)

annotated_image = mask_annotator.annotate(
    scene=image, detections=detections)
annotated_image = label_annotator.annotate(
    scene=annotated_image, detections=detections)

import supervision as sv
from ultralytics import YOLO

model = YOLO(<SOURCE_MODEL_PATH>)
csv_sink = sv.CSVSink(<RESULT_CSV_FILE_PATH>)
frames_generator = sv.get_video_frames_generator(<SOURCE_VIDEO_PATH>)

with csv_sink:
    for frame in frames_generator:
        result = model(frame)[0]
        detections = sv.Detections.from_ultralytics(result)
        csv_sink.append(detections, custom_data={<CUSTOM_LABEL>:<CUSTOM_DATA>})

import supervision as sv
from ultralytics import YOLO

model = YOLO(<SOURCE_MODEL_PATH>)
json_sink = sv.JSONSink(<RESULT_JSON_FILE_PATH>)
frames_generator = sv.get_video_frames_generator(<SOURCE_VIDEO_PATH>)

with json_sink:
    for frame in frames_generator:
        result = model(frame)[0]
        detections = sv.Detections.from_ultralytics(result)
        json_sink.append(detections, custom_data={<CUSTOM_LABEL>:<CUSTOM_DATA>})

import cv2
import supervision as sv
from inference import get_model

image = cv2.imread(<SOURCE_IMAGE_PATH>)
model = get_model(model_id="yolov8n-640")

result = model.infer(image)[0]
detections = sv.Detections.from_inference(result)

crop_annotator = sv.CropAnnotator()
annotated_frame = crop_annotator.annotate(
    scene=image.copy(),
    detections=detections
)

>>> import supervision as sv

>>> image = ...
>>> detections = sv.Detections(...)

>>> percentage_bar_annotator = sv.PercentageBarAnnotator()
>>> annotated_frame = percentage_bar_annotator.annotate(
...     scene=image.copy(),
...     detections=detections
... )

import cv2
import supervision as sv
from ultralytics import YOLO

image = cv2.imread(<SOURCE_IMAGE_PATH>)
model = YOLO("yolov8n-obb.pt")

result = model(image)[0]
detections = sv.Detections.from_ultralytics(result)

oriented_box_annotator = sv.OrientedBoxAnnotator()
annotated_frame = oriented_box_annotator.annotate(
    scene=image.copy(),
    detections=detections
)

>>> import supervision as sv

>>> sv.ColorPalette.from_matplotlib('viridis', 5)
ColorPalette(colors=[Color(r=68, g=1, b=84), Color(r=59, g=82, b=139), ...])

>>> import supervision as sv

>>> image = ...
>>> detections = sv.Detections(...)

>>> polygon_annotator = sv.PolygonAnnotator()
>>> annotated_frame = polygon_annotator.annotate(
...     scene=image.copy(),
...     detections=detections
... )

>>> from supervision.assets import download_assets, VideoAssets
>>> download_assets(VideoAssets.VEHICLES)
"vehicles.mp4"

>>> import supervision as sv

>>> image = ...
>>> detections = sv.Detections(...)

>>> halo_annotator = sv.HaloAnnotator()
>>> annotated_frame = halo_annotator.annotate(
...     scene=image.copy(),
...     detections=detections
... )

>>> import supervision as sv

>>> image = ...
>>> detections = sv.Detections(...)

>>> bounding_box_annotator = sv.BoundingBoxAnnotator()
>>> annotated_frame = bounding_box_annotator.annotate(
...     scene=image.copy(),
...     detections=detections
... )

>>> import cv2
>>> import supervision as sv
>>> from ultralytics import YOLO

>>> image = cv2.imread(SOURCE_IMAGE_PATH)
>>> model = YOLO(...)

>>> def callback(image_slice: np.ndarray) -> sv.Detections:
...     result = model(image_slice)[0]
...     return sv.Detections.from_ultralytics(result)

>>> slicer = sv.InferenceSlicer(callback = callback)

>>> detections = slicer(image)

>>> import supervision as sv
>>> from ultralytics import YOLO

>>> dataset = sv.DetectionDataset.from_yolo(...)

>>> model = YOLO(...)
>>> def callback(image: np.ndarray) -> sv.Detections:
...     result = model(image)[0]
...     return sv.Detections.from_yolov8(result)

>>> mean_average_precision = sv.MeanAveragePrecision.benchmark(
...     dataset = dataset,
...     callback = callback
... )

>>> mean_average_precision.map50_95
0.433

>>> import supervision as sv
>>> from ultralytics import YOLO

>>> dataset = sv.DetectionDataset.from_yolo(...)

>>> model = YOLO(...)
>>> def callback(image: np.ndarray) -> sv.Detections:
...     result = model(image)[0]
...     return sv.Detections.from_yolov8(result)

>>> confusion_matrix = sv.ConfusionMatrix.benchmark(
...     dataset = dataset,
...     callback = callback
... )

>>> confusion_matrix.matrix
array([
    [0., 0., 0., 0.],
    [0., 1., 0., 1.],
    [0., 1., 1., 0.],
    [1., 1., 0., 0.]
])

>>> import supervision as sv

>>> ds = sv.DetectionDataset.from_coco(
...     images_directory_path='...',
...     annotations_path='...'
... )

>>> ds.as_coco(
...     images_directory_path='...',
...     annotations_path='...'
... )

>>> import supervision as sv

>>> 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']

>>> import supervision as sv

>>> cs = sv.ClassificationDataset.from_folder_structure(
...     root_directory_path='...'
... )

>>> cs.as_folder_structure(
...     root_directory_path='...'
... )

>>> import supervision as sv

>>> detections = sv.Detections(...)
>>> len(detections[0])
1
>>> len(detections[[0, 1]])
2
>>> len(detections[0:2])
2

>>> import supervision as sv

>>> with sv.ImageSink(target_dir_path='target/directory/path') as sink:
...     for image in sv.get_video_frames_generator(source_path='source_video.mp4', stride=10):
...         sink.save_image(image=image)

>>> import roboflow
>>> from roboflow import Roboflow
>>> import supervision as sv

>>> roboflow.login()

>>> rf = Roboflow()

>>> project = rf.workspace(WORKSPACE_ID).project(PROJECT_ID)
>>> dataset = project.version(PROJECT_VERSION).download("yolov5")

>>> ds = sv.DetectionDataset.from_yolo(
...     images_directory_path=f"{dataset.location}/train/images",
...     annotations_directory_path=f"{dataset.location}/train/labels",
...     data_yaml_path=f"{dataset.location}/data.yaml"
... )

>>> ds.classes
['dog', 'person']

>>> import supervision as sv

>>> ds = sv.DetectionDataset(...)
>>> train_ds, test_ds = ds.split(split_ratio=0.7, random_state=42, shuffle=True)

>>> len(train_ds), len(test_ds)
(700, 300)