Skip to content

Reference for ultralytics/models/nas/val.py

Improvements

This page is sourced from https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/nas/val.py. Have an improvement or example to add? Open a Pull Request — thank you! 🙏


Summary

class ultralytics.models.nas.val.NASValidator

NASValidator()

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

NameTypeDescription
argsNamespaceNamespace containing various configurations for post-processing, such as confidence and IoU thresholds.
lbtorch.TensorOptional tensor for multilabel NMS.

Methods

NameDescription
postprocessApply Non-maximum suppression to prediction outputs.

Examples

>>> from ultralytics import NAS
>>> model = NAS("yolo_nas_s")
>>> validator = model.validator
>>> # Assumes that raw_preds are available
>>> final_preds = validator.postprocess(raw_preds)

Notes

This class is generally not instantiated directly but is used internally within the NAS class.

Source code in ultralytics/models/nas/val.pyView on GitHub
class NASValidator(DetectionValidator):


method ultralytics.models.nas.val.NASValidator.postprocess

def postprocess(self, preds_in)

Apply Non-maximum suppression to prediction outputs.

Args

NameTypeDescriptionDefault
preds_inrequired
Source code in ultralytics/models/nas/val.pyView on GitHub
def postprocess(self, preds_in):
    """Apply Non-maximum suppression to prediction outputs."""
    boxes = ops.xyxy2xywh(preds_in[0][0])  # Convert bounding box format from xyxy to xywh
    preds = torch.cat((boxes, preds_in[0][1]), -1).permute(0, 2, 1)  # Concatenate boxes with scores and permute
    return super().postprocess(preds)





📅 Created 2 years ago ✏️ Updated 2 days ago
glenn-jocherjk4eBurhan-Q