89 lines
4.1 KiB
Python
89 lines
4.1 KiB
Python
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
|
|
|
|
from ultralytics.engine.results import Results
|
|
from ultralytics.models.yolo.detect.predict import DetectionPredictor
|
|
from ultralytics.utils import DEFAULT_CFG, ops
|
|
|
|
|
|
class SegmentationPredictor(DetectionPredictor):
|
|
"""
|
|
A class extending the DetectionPredictor class for prediction based on a segmentation model.
|
|
|
|
This class specializes in processing segmentation model outputs, handling both bounding boxes and masks in the
|
|
prediction results.
|
|
|
|
Attributes:
|
|
args (Dict): Configuration arguments for the predictor.
|
|
model (torch.nn.Module): The loaded YOLO segmentation model.
|
|
batch (List): Current batch of images being processed.
|
|
|
|
Methods:
|
|
postprocess: Applies non-max suppression and processes detections.
|
|
construct_results: Constructs a list of result objects from predictions.
|
|
construct_result: Constructs a single result object from a prediction.
|
|
|
|
Examples:
|
|
>>> from ultralytics.utils import ASSETS
|
|
>>> from ultralytics.models.yolo.segment import SegmentationPredictor
|
|
>>> args = dict(model="yolo11n-seg.pt", source=ASSETS)
|
|
>>> predictor = SegmentationPredictor(overrides=args)
|
|
>>> predictor.predict_cli()
|
|
"""
|
|
|
|
def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
|
|
"""Initialize the SegmentationPredictor with configuration, overrides, and callbacks."""
|
|
super().__init__(cfg, overrides, _callbacks)
|
|
self.args.task = "segment"
|
|
|
|
def postprocess(self, preds, img, orig_imgs):
|
|
"""Apply non-max suppression and process detections for each image in the input batch."""
|
|
# Extract protos - tuple if PyTorch model or array if exported
|
|
protos = preds[1][-1] if isinstance(preds[1], tuple) else preds[1]
|
|
return super().postprocess(preds[0], img, orig_imgs, protos=protos)
|
|
|
|
def construct_results(self, preds, img, orig_imgs, protos):
|
|
"""
|
|
Construct a list of result objects from the predictions.
|
|
|
|
Args:
|
|
preds (List[torch.Tensor]): List of predicted bounding boxes, scores, and masks.
|
|
img (torch.Tensor): The image after preprocessing.
|
|
orig_imgs (List[np.ndarray]): List of original images before preprocessing.
|
|
protos (List[torch.Tensor]): List of prototype masks.
|
|
|
|
Returns:
|
|
(List[Results]): List of result objects containing the original images, image paths, class names,
|
|
bounding boxes, and masks.
|
|
"""
|
|
return [
|
|
self.construct_result(pred, img, orig_img, img_path, proto)
|
|
for pred, orig_img, img_path, proto in zip(preds, orig_imgs, self.batch[0], protos)
|
|
]
|
|
|
|
def construct_result(self, pred, img, orig_img, img_path, proto):
|
|
"""
|
|
Construct a single result object from the prediction.
|
|
|
|
Args:
|
|
pred (np.ndarray): The predicted bounding boxes, scores, and masks.
|
|
img (torch.Tensor): The image after preprocessing.
|
|
orig_img (np.ndarray): The original image before preprocessing.
|
|
img_path (str): The path to the original image.
|
|
proto (torch.Tensor): The prototype masks.
|
|
|
|
Returns:
|
|
(Results): Result object containing the original image, image path, class names, bounding boxes, and masks.
|
|
"""
|
|
if not len(pred): # save empty boxes
|
|
masks = None
|
|
elif self.args.retina_masks:
|
|
pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
|
|
masks = ops.process_mask_native(proto, pred[:, 6:], pred[:, :4], orig_img.shape[:2]) # HWC
|
|
else:
|
|
masks = ops.process_mask(proto, pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True) # HWC
|
|
pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
|
|
if masks is not None:
|
|
keep = masks.sum((-2, -1)) > 0 # only keep predictions with masks
|
|
pred, masks = pred[keep], masks[keep]
|
|
return Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], masks=masks)
|