mirror of
https://github.com/THU-MIG/yolov10.git
synced 2025-05-23 21:44:22 +08:00
8596ee241f
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
51 lines
2.5 KiB
Python
51 lines
2.5 KiB
Python
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
|
|
|
import torch
|
|
|
|
from ultralytics.engine.results import Results
|
|
from ultralytics.models.fastsam.utils import bbox_iou
|
|
from ultralytics.models.yolo.detect.predict import DetectionPredictor
|
|
from ultralytics.utils import DEFAULT_CFG, ops
|
|
|
|
|
|
class FastSAMPredictor(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):
|
|
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)
|
|
full_box = torch.zeros(p[0].shape[1])
|
|
full_box[2], full_box[3], full_box[4], full_box[6:] = img.shape[3], img.shape[2], 1.0, 1.0
|
|
full_box = full_box.view(1, -1)
|
|
critical_iou_index = bbox_iou(full_box[0][:4], p[0][:, :4], iou_thres=0.9, image_shape=img.shape[2:])
|
|
if critical_iou_index.numel() != 0:
|
|
full_box[0][4] = p[0][critical_iou_index][:, 4]
|
|
full_box[0][6:] = p[0][critical_iou_index][:, 6:]
|
|
p[0][critical_iou_index] = full_box
|
|
results = []
|
|
is_list = isinstance(orig_imgs, list) # input images are a list, not a torch.Tensor
|
|
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 is_list else orig_imgs
|
|
img_path = self.batch[0][i]
|
|
if not len(pred): # save empty boxes
|
|
masks = None
|
|
elif self.args.retina_masks:
|
|
if is_list:
|
|
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 is_list:
|
|
pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
|
|
results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], masks=masks))
|
|
return results
|