Spaces:
Sleeping
Sleeping
File size: 1,902 Bytes
e5dd705 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
# Ultralytics YOLO 🚀, AGPL-3.0 license
import torch
from ultralytics.yolo.data.augment import LetterBox
from ultralytics.yolo.engine.predictor import BasePredictor
from ultralytics.yolo.engine.results import Results
from ultralytics.yolo.utils import ops
class RTDETRPredictor(BasePredictor):
def postprocess(self, preds, img, orig_imgs):
"""Postprocess predictions and returns a list of Results objects."""
bboxes, scores = preds[:2] # (1, bs, 300, 4), (1, bs, 300, nc)
bboxes, scores = bboxes.squeeze_(0), scores.squeeze_(0)
results = []
for i, bbox in enumerate(bboxes): # (300, 4)
bbox = ops.xywh2xyxy(bbox)
score, cls = scores[i].max(-1, keepdim=True) # (300, 1)
idx = score.squeeze(-1) > self.args.conf # (300, )
if self.args.classes is not None:
idx = (cls == torch.tensor(self.args.classes, device=cls.device)).any(1) & idx
pred = torch.cat([bbox, score, cls], dim=-1)[idx] # filter
orig_img = orig_imgs[i] if isinstance(orig_imgs, list) else orig_imgs
oh, ow = orig_img.shape[:2]
if not isinstance(orig_imgs, torch.Tensor):
pred[..., [0, 2]] *= ow
pred[..., [1, 3]] *= oh
path = self.batch[0]
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))
return results
def pre_transform(self, im):
"""Pre-transform input image before inference.
Args:
im (List(np.ndarray)): (N, 3, h, w) for tensor, [(h, w, 3) x N] for list.
Return: A list of transformed imgs.
"""
# The size must be square(640) and scaleFilled.
return [LetterBox(self.imgsz, auto=False, scaleFill=True)(image=x) for x in im]
|