Skip to content

检测与标注

Supervision 提供了一个无缝的流程，用于标注各种目标检测和分割模型生成的预测结果。本指南将展示如何使用 Inference、Ultralytics 或 Transformers 包执行推理。之后，您将了解如何将这些预测结果导入 Supervision，并用于标注源图像。

basic-annotation

运行检测

首先，您需要从目标检测或分割模型中获取预测结果。

import cv2
from inference import get_model

model = get_model(model_id="yolov8n-640")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model.infer(image)[0]

import cv2
from ultralytics import YOLO

model = YOLO("yolov8n.pt")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model(image)[0]

import torch
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]

将预测结果加载到 Supervision

现在我们已经从模型中获得了预测结果，可以将其加载到 Supervision 中。

我们可以使用 sv.Detections.from_inference 方法，该方法同时接受来自检测和分割模型的模型结果。

import cv2
import supervision as sv
from inference import get_model

model = get_model(model_id="yolov8n-640")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)

我们可以使用 sv.Detections.from_ultralytics 方法，该方法同时接受来自检测和分割模型的模型结果。

import cv2
import supervision as sv
from ultralytics import YOLO

model = YOLO("yolov8n.pt")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)

我们可以使用 sv.Detections.from_transformers 方法，该方法同时接受来自检测和分割模型的模型结果。

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)

您可以使用以下方法从其他计算机视觉框架和库加载预测结果：

使用检测结果标注图像

最后，我们可以用预测结果标注图像。由于我们使用的是目标检测模型，我们将使用 sv.BoxAnnotator 和 sv.LabelAnnotator 类。

import cv2
import supervision as sv
from inference import get_model

model = get_model(model_id="yolov8n-640")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)

box_annotator = sv.BoxAnnotator()
label_annotator = sv.LabelAnnotator()

annotated_image = box_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

model = YOLO("yolov8n.pt")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)

box_annotator = sv.BoxAnnotator()
label_annotator = sv.LabelAnnotator()

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

box_annotator = sv.BoxAnnotator()
label_annotator = sv.LabelAnnotator()

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

basic-annotation

显示自定义标签

默认情况下，sv.LabelAnnotator 会使用 class_name（如果可能）或 class_id 来标记每个检测结果。您可以通过将自定义 labels 列表传递给 annotate 方法来覆盖此行为。

import cv2
import supervision as sv
from inference import get_model

model = get_model(model_id="yolov8n-640")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)

box_annotator = sv.BoxAnnotator()
label_annotator = sv.LabelAnnotator()

labels = [
    f"{class_name} {confidence:.2f}"
    for class_name, confidence
    in zip(detections['class_name'], detections.confidence)
]

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

import cv2
import supervision as sv
from ultralytics import YOLO

model = YOLO("yolov8n.pt")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)

box_annotator = sv.BoxAnnotator()
label_annotator = sv.LabelAnnotator()

labels = [
    f"{class_name} {confidence:.2f}"
    for class_name, confidence
    in zip(detections['class_name'], detections.confidence)
]

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

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)

box_annotator = sv.BoxAnnotator()
label_annotator = sv.LabelAnnotator()

labels = [
    f"{class_name} {confidence:.2f}"
    for class_name, confidence
    in zip(detections['class_name'], detections.confidence)
]

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

custom-label-annotation

使用分割结果标注图像

如果您运行的是分割模型，sv.MaskAnnotator 是 sv.BoxAnnotator 的一个直接替代品，它允许您绘制掩码而不是边界框。

import cv2
import supervision as sv
from inference import get_model

model = get_model(model_id="yolov8n-seg-640")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)

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

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

model = YOLO("yolov8n-seg.pt")
image = cv2.imread(<SOURCE_IMAGE_PATH>)
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)

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

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

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(
    transformers_results=results,
    id2label=model.config.id2label)

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

labels = [
    f"{class_name} {confidence:.2f}"
    for class_name, confidence
    in zip(detections['class_name'], detections.confidence)
]

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

segmentation-annotation

Comments