You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
104 lines
4.5 KiB
104 lines
4.5 KiB
# Ultralytics YOLO 🚀, GPL-3.0 license
|
|
|
|
from ultralytics.yolo.engine.results import Results
|
|
from ultralytics.yolo.utils import DEFAULT_CFG, ROOT, ops
|
|
from ultralytics.yolo.utils.plotting import colors, save_one_box
|
|
from ultralytics.yolo.v8.detect.predict import DetectionPredictor
|
|
|
|
|
|
class PosePredictor(DetectionPredictor):
|
|
|
|
def postprocess(self, preds, img, orig_img):
|
|
preds = ops.non_max_suppression(preds,
|
|
self.args.conf,
|
|
self.args.iou,
|
|
agnostic=self.args.agnostic_nms,
|
|
max_det=self.args.max_det,
|
|
classes=self.args.classes,
|
|
nc=len(self.model.names))
|
|
|
|
results = []
|
|
for i, pred in enumerate(preds):
|
|
orig_img = orig_img[i] if isinstance(orig_img, list) else orig_img
|
|
shape = orig_img.shape
|
|
pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], shape).round()
|
|
pred_kpts = pred[:, 6:].view(len(pred), *self.model.kpt_shape) if len(pred) else pred[:, 6:]
|
|
pred_kpts = ops.scale_coords(img.shape[2:], pred_kpts, shape)
|
|
path, _, _, _, _ = self.batch
|
|
img_path = path[i] if isinstance(path, list) else path
|
|
results.append(
|
|
Results(orig_img=orig_img,
|
|
path=img_path,
|
|
names=self.model.names,
|
|
boxes=pred[:, :6],
|
|
keypoints=pred_kpts))
|
|
return results
|
|
|
|
def write_results(self, idx, results, batch):
|
|
p, im, im0 = batch
|
|
log_string = ''
|
|
if len(im.shape) == 3:
|
|
im = im[None] # expand for batch dim
|
|
self.seen += 1
|
|
imc = im0.copy() if self.args.save_crop else im0
|
|
if self.source_type.webcam or self.source_type.from_img: # batch_size >= 1
|
|
log_string += f'{idx}: '
|
|
frame = self.dataset.count
|
|
else:
|
|
frame = getattr(self.dataset, 'frame', 0)
|
|
self.data_path = p
|
|
self.txt_path = str(self.save_dir / 'labels' / p.stem) + ('' if self.dataset.mode == 'image' else f'_{frame}')
|
|
log_string += '%gx%g ' % im.shape[2:] # print string
|
|
self.annotator = self.get_annotator(im0)
|
|
|
|
det = results[idx].boxes # TODO: make boxes inherit from tensors
|
|
if len(det) == 0:
|
|
return f'{log_string}(no detections), '
|
|
for c in det.cls.unique():
|
|
n = (det.cls == c).sum() # detections per class
|
|
log_string += f"{n} {self.model.names[int(c)]}{'s' * (n > 1)}, "
|
|
|
|
kpts = reversed(results[idx].keypoints)
|
|
for k in kpts:
|
|
self.annotator.kpts(k, shape=results[idx].orig_shape)
|
|
|
|
# write
|
|
for j, d in enumerate(reversed(det)):
|
|
c, conf, id = int(d.cls), float(d.conf), None if d.id is None else int(d.id.item())
|
|
if self.args.save_txt: # Write to file
|
|
kpt = (kpts[j][:, :2] / d.orig_shape[[1, 0]]).reshape(-1).tolist()
|
|
box = d.xywhn.view(-1).tolist()
|
|
line = (c, *box, *kpt) + (conf, ) * self.args.save_conf + (() if id is None else (id, ))
|
|
with open(f'{self.txt_path}.txt', 'a') as f:
|
|
f.write(('%g ' * len(line)).rstrip() % line + '\n')
|
|
if self.args.save or self.args.show: # Add bbox to image
|
|
name = ('' if id is None else f'id:{id} ') + self.model.names[c]
|
|
label = (f'{name} {conf:.2f}' if self.args.show_conf else name) if self.args.show_labels else None
|
|
if self.args.boxes:
|
|
self.annotator.box_label(d.xyxy.squeeze(), label, color=colors(c, True))
|
|
if self.args.save_crop:
|
|
save_one_box(d.xyxy,
|
|
imc,
|
|
file=self.save_dir / 'crops' / self.model.model.names[c] / f'{self.data_path.stem}.jpg',
|
|
BGR=True)
|
|
|
|
return log_string
|
|
|
|
|
|
def predict(cfg=DEFAULT_CFG, use_python=False):
|
|
model = cfg.model or 'yolov8n-pose.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 = PosePredictor(overrides=args)
|
|
predictor.predict_cli()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
predict()
|