ultralytics/yolo/v8/segment/predict.py

# Ultralytics YOLO 🚀, AGPL-3.0 license

import torch

from ultralytics.yolo.engine.results import Results
from ultralytics.yolo.utils import DEFAULT_CFG, ROOT, ops
from ultralytics.yolo.v8.detect.predict import DetectionPredictor


class SegmentationPredictor(DetectionPredictor):

    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
        super().__init__(cfg, overrides, _callbacks)
        self.args.task = 'segment'

    def postprocess(self, preds, img, orig_imgs):
        """TODO: filter by classes."""
        p = ops.non_max_suppression(preds[0],
                                    self.args.conf,
                                    self.args.iou,
                                    agnostic=self.args.agnostic_nms,
                                    max_det=self.args.max_det,
                                    nc=len(self.model.names),
                                    classes=self.args.classes)
        results = []
        proto = preds[1][-1] if len(preds[1]) == 3 else preds[1]  # second output is len 3 if pt, but only 1 if exported
        for i, pred in enumerate(p):
            orig_img = orig_imgs[i] if isinstance(orig_imgs, list) else orig_imgs
            path = self.batch[0]
            img_path = path[i] if isinstance(path, list) else path
            if not len(pred):  # save empty boxes
                results.append(Results(orig_img=orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6]))
                continue
            if self.args.retina_masks:
                if not isinstance(orig_imgs, torch.Tensor):
                    pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
                masks = ops.process_mask_native(proto[i], pred[:, 6:], pred[:, :4], orig_img.shape[:2])  # HWC
            else:
                masks = ops.process_mask(proto[i], pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True)  # HWC
                if not isinstance(orig_imgs, torch.Tensor):
                    pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
            results.append(
                Results(orig_img=orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], masks=masks))
        return results


def predict(cfg=DEFAULT_CFG, use_python=False):
    """Runs YOLO object detection on an image or video source."""
    model = cfg.model or 'yolov8n-seg.pt'
    source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \
        else 'https://ultralytics.com/images/bus.jpg'

    args = dict(model=model, source=source)
    if use_python:
        from ultralytics import YOLO
        YOLO(model)(**args)
    else:
        predictor = SegmentationPredictor(overrides=args)
        predictor.predict_cli()


if __name__ == '__main__':
    predict()