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.
98 lines
3.9 KiB
98 lines
3.9 KiB
import hydra
|
|
import torch
|
|
|
|
from ultralytics.yolo.engine.predictor import BasePredictor
|
|
from ultralytics.yolo.engine.trainer import DEFAULT_CONFIG
|
|
from ultralytics.yolo.utils import ops
|
|
from ultralytics.yolo.utils.plotting import Annotator, colors, save_one_box
|
|
|
|
|
|
class DetectionPredictor(BasePredictor):
|
|
|
|
def get_annotator(self, img):
|
|
return Annotator(img, line_width=self.args.line_thickness, example=str(self.model.names))
|
|
|
|
def preprocess(self, img):
|
|
img = torch.from_numpy(img).to(self.model.device)
|
|
img = img.half() if self.model.fp16 else img.float() # uint8 to fp16/32
|
|
img /= 255 # 0 - 255 to 0.0 - 1.0
|
|
return img
|
|
|
|
def postprocess(self, preds, img, orig_img):
|
|
preds = ops.non_max_suppression(preds,
|
|
self.args.conf_thres,
|
|
self.args.iou_thres,
|
|
agnostic=self.args.agnostic_nms,
|
|
max_det=self.args.max_det)
|
|
|
|
for i, pred in enumerate(preds):
|
|
shape = orig_img[i].shape if self.webcam else orig_img.shape
|
|
pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], shape).round()
|
|
|
|
return preds
|
|
|
|
def write_results(self, idx, preds, batch):
|
|
p, im, im0 = batch
|
|
log_string = ""
|
|
if len(im.shape) == 3:
|
|
im = im[None] # expand for batch dim
|
|
self.seen += 1
|
|
im0 = im0.copy()
|
|
if self.webcam: # batch_size >= 1
|
|
log_string += f'{idx}: '
|
|
frame = self.dataset.count
|
|
else:
|
|
frame = getattr(self.dataset, 'frame', 0)
|
|
|
|
self.data_path = p
|
|
# save_path = str(self.save_dir / p.name) # im.jpg
|
|
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 = preds[idx]
|
|
if len(det) == 0:
|
|
return log_string
|
|
for c in det[:, 5].unique():
|
|
n = (det[:, 5] == c).sum() # detections per class
|
|
log_string += f"{n} {self.model.names[int(c)]}{'s' * (n > 1)}, "
|
|
|
|
# write
|
|
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
|
|
for *xyxy, conf, cls in reversed(det):
|
|
if self.args.save_txt: # Write to file
|
|
xywh = (ops.xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
|
|
line = (cls, *xywh, conf) if self.args.save_conf else (cls, *xywh) # label format
|
|
with open(f'{self.txt_path}.txt', 'a') as f:
|
|
f.write(('%g ' * len(line)).rstrip() % line + '\n')
|
|
|
|
if self.save_img or self.args.save_crop or self.args.view_img: # Add bbox to image
|
|
c = int(cls) # integer class
|
|
label = None if self.args.hide_labels else (
|
|
self.model.names[c] if self.args.hide_conf else f'{self.model.names[c]} {conf:.2f}')
|
|
self.annotator.box_label(xyxy, label, color=colors(c, True))
|
|
if self.args.save_crop:
|
|
imc = im0.copy()
|
|
save_one_box(xyxy,
|
|
imc,
|
|
file=self.save_dir / 'crops' / self.model.model.names[c] / f'{self.data_path.stem}.jpg',
|
|
BGR=True)
|
|
|
|
return log_string
|
|
|
|
|
|
@hydra.main(version_base=None, config_path=str(DEFAULT_CONFIG.parent), config_name=DEFAULT_CONFIG.name)
|
|
def predict(cfg):
|
|
cfg.model = cfg.model or "n.pt"
|
|
sz = cfg.imgsz
|
|
if type(sz) != int: # received listConfig
|
|
cfg.imgsz = [sz[0], sz[0]] if len(cfg.imgsz) == 1 else [sz[0], sz[1]] # expand
|
|
else:
|
|
cfg.imgsz = [sz, sz]
|
|
predictor = DetectionPredictor(cfg)
|
|
predictor()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
predict()
|