84 lines
2.9 KiB
Python
84 lines
2.9 KiB
Python
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
|
|
|
from ultralytics.engine.predictor import BasePredictor
|
|
from ultralytics.engine.results import Results
|
|
from ultralytics.utils import ops
|
|
|
|
import numpy as np
|
|
import torch
|
|
|
|
|
|
class DetectionPredictor(BasePredictor):
|
|
"""
|
|
A class extending the BasePredictor class for prediction based on a detection model.
|
|
|
|
Example:
|
|
```python
|
|
from ultralytics.utils import ASSETS
|
|
from ultralytics.models.yolo.detect import DetectionPredictor
|
|
|
|
args = dict(model='yolov8n.pt', source=ASSETS)
|
|
predictor = DetectionPredictor(overrides=args)
|
|
predictor.predict_cli()
|
|
```
|
|
"""
|
|
|
|
def preprocess(self, im):
|
|
"""
|
|
Prepares input image before inference.
|
|
|
|
Args:
|
|
im (torch.Tensor | List(np.ndarray)): BCHW for tensor, [(HWC) x B] for list.
|
|
"""
|
|
not_tensor = not isinstance(im, torch.Tensor)
|
|
if not_tensor:
|
|
im = np.stack(self.pre_transform(im))
|
|
im_rgb = im.copy()
|
|
# for i in range(im.shape[3] // 3):
|
|
# start_idx = i * 3
|
|
# channel_idx = list(range(start_idx, start_idx + 3))
|
|
# im_rgb[..., channel_idx] = im[..., channel_idx][:, :, ::-1] # BGR to RGB
|
|
im = im_rgb.transpose((0, 3, 1, 2)) # BHWC to BCHW
|
|
im = np.ascontiguousarray(im) # contiguous
|
|
im = torch.from_numpy(im)
|
|
|
|
im = im.to(self.device)
|
|
im = im.half() if self.model.fp16 else im.float() # uint8 to fp16/32
|
|
if not_tensor:
|
|
im /= 255 # 0 - 255 to 0.0 - 1.0
|
|
return im
|
|
|
|
def postprocess(self, preds, img, orig_imgs):
|
|
"""Post-processes predictions and returns a list of Results objects."""
|
|
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,
|
|
)
|
|
|
|
if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list
|
|
orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)
|
|
|
|
results = []
|
|
for i, pred in enumerate(preds):
|
|
orig_img = orig_imgs[i]
|
|
pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
|
|
# pred = self.fliplr(pred, orig_img.shape[1])
|
|
img_path = self.batch[0][i]
|
|
results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred))
|
|
return results
|
|
|
|
def fliplr(self, pred, w):
|
|
"""Reverses the order of the bounding boxes and segments horizontally."""
|
|
bboxes = pred.clone()
|
|
if True: # "xyxy"
|
|
x1 = bboxes[:, 0].clone()
|
|
x2 = bboxes[:, 2].clone()
|
|
bboxes[:, 0] = w - x2
|
|
bboxes[:, 2] = w - x1
|
|
else:
|
|
bboxes[:, 0] = w - bboxes[:, 0]
|
|
return bboxes |