84 lines
3.5 KiB
Python
84 lines
3.5 KiB
Python
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
|
|
|
|
from ultralytics.engine.predictor import BasePredictor
|
|
from ultralytics.engine.results import Results
|
|
from ultralytics.utils import ops
|
|
|
|
|
|
class DetectionPredictor(BasePredictor):
|
|
"""
|
|
A class extending the BasePredictor class for prediction based on a detection model.
|
|
|
|
This predictor specializes in object detection tasks, processing model outputs into meaningful detection results
|
|
with bounding boxes and class predictions.
|
|
|
|
Attributes:
|
|
args (namespace): Configuration arguments for the predictor.
|
|
model (nn.Module): The detection model used for inference.
|
|
batch (List): Batch of images and metadata for processing.
|
|
|
|
Methods:
|
|
postprocess: Process raw model predictions into detection results.
|
|
construct_results: Build Results objects from processed predictions.
|
|
construct_result: Create a single Result object from a prediction.
|
|
|
|
Examples:
|
|
>>> from ultralytics.utils import ASSETS
|
|
>>> from ultralytics.models.yolo.detect import DetectionPredictor
|
|
>>> args = dict(model="yolo11n.pt", source=ASSETS)
|
|
>>> predictor = DetectionPredictor(overrides=args)
|
|
>>> predictor.predict_cli()
|
|
"""
|
|
|
|
def postprocess(self, preds, img, orig_imgs, **kwargs):
|
|
"""Post-processes predictions and returns a list of Results objects."""
|
|
preds = ops.non_max_suppression(
|
|
preds,
|
|
self.args.conf,
|
|
self.args.iou,
|
|
self.args.classes,
|
|
self.args.agnostic_nms,
|
|
max_det=self.args.max_det,
|
|
nc=len(self.model.names),
|
|
end2end=getattr(self.model, "end2end", False),
|
|
rotated=self.args.task == "obb",
|
|
)
|
|
|
|
if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list
|
|
orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)
|
|
|
|
return self.construct_results(preds, img, orig_imgs, **kwargs)
|
|
|
|
def construct_results(self, preds, img, orig_imgs):
|
|
"""
|
|
Construct a list of Results objects from model predictions.
|
|
|
|
Args:
|
|
preds (List[torch.Tensor]): List of predicted bounding boxes and scores for each image.
|
|
img (torch.Tensor): Batch of preprocessed images used for inference.
|
|
orig_imgs (List[np.ndarray]): List of original images before preprocessing.
|
|
|
|
Returns:
|
|
(List[Results]): List of Results objects containing detection information for each image.
|
|
"""
|
|
return [
|
|
self.construct_result(pred, img, orig_img, img_path)
|
|
for pred, orig_img, img_path in zip(preds, orig_imgs, self.batch[0])
|
|
]
|
|
|
|
def construct_result(self, pred, img, orig_img, img_path):
|
|
"""
|
|
Construct a single Results object from one image prediction.
|
|
|
|
Args:
|
|
pred (torch.Tensor): Predicted boxes and scores with shape (N, 6) where N is the number of detections.
|
|
img (torch.Tensor): Preprocessed image tensor used for inference.
|
|
orig_img (np.ndarray): Original image before preprocessing.
|
|
img_path (str): Path to the original image file.
|
|
|
|
Returns:
|
|
(Results): Results object containing the original image, image path, class names, and scaled bounding boxes.
|
|
"""
|
|
pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
|
|
return Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6])
|