NASValidator(
dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None
)
Bases: DetectionValidator
Ultralytics YOLO NAS Validator for object detection.
Extends DetectionValidator from the Ultralytics models package and is designed to post-process the raw predictions generated by YOLO NAS models. It performs non-maximum suppression to remove overlapping and low-confidence boxes, ultimately producing the final detections.
Attributes:
| Name | Type | Description |
|---|
args | Namespace | Namespace containing various configurations for post-processing, such as confidence and IoU. |
lb | Tensor | Optional tensor for multilabel NMS. |
Example
from ultralytics import NAS
model = NAS("yolo_nas_s")
validator = model.validator
# Assumes that raw_preds are available
final_preds = validator.postprocess(raw_preds)
Note
This class is generally not instantiated directly but is used internally within the NAS class.
Source code in ultralytics/models/yolo/detect/val.py
| def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None):
"""Initialize detection model with necessary variables and settings."""
super().__init__(dataloader, save_dir, pbar, args, _callbacks)
self.nt_per_class = None
self.nt_per_image = None
self.is_coco = False
self.is_lvis = False
self.class_map = None
self.args.task = "detect"
self.metrics = DetMetrics(save_dir=self.save_dir, on_plot=self.on_plot)
self.iouv = torch.linspace(0.5, 0.95, 10) # IoU vector for mAP@0.5:0.95
self.niou = self.iouv.numel()
self.lb = [] # for autolabelling
if self.args.save_hybrid:
LOGGER.warning(
"WARNING ⚠️ 'save_hybrid=True' will append ground truth to predictions for autolabelling.\n"
"WARNING ⚠️ 'save_hybrid=True' will cause incorrect mAP.\n"
)
|
Apply Non-maximum suppression to prediction outputs.
Source code in ultralytics/models/nas/val.py
| def postprocess(self, preds_in):
"""Apply Non-maximum suppression to prediction outputs."""
boxes = ops.xyxy2xywh(preds_in[0][0])
preds = torch.cat((boxes, preds_in[0][1]), -1).permute(0, 2, 1)
return ops.non_max_suppression(
preds,
self.args.conf,
self.args.iou,
labels=self.lb,
multi_label=False,
agnostic=self.args.single_cls or self.args.agnostic_nms,
max_det=self.args.max_det,
max_time_img=0.5,
)
|
