HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.0.239 Ultralytics Actions and hub-sdk adoption (#7431)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Burhan <62214284+Burhan-Q@users.noreply.github.com>
Co-authored-by: Kayzwer <68285002+Kayzwer@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2024-01-10 03:16:08 +01:00 • committed by GitHub
parent e795277391
commit fe27db2f6e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
139 changed files with 6870 additions and 5125 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ultralytics/models/nas/__init__.py
View file

@ -4,4 +4,4 @@ from .model import NAS
from .predict import NASPredictor
from .val import NASValidator
__all__ = 'NASPredictor', 'NASValidator', 'NAS'
__all__ = "NASPredictor", "NASValidator", "NAS"

17
ultralytics/models/nas/model.py
View file

@ -44,20 +44,21 @@ class NAS(Model):
YOLO-NAS models only support pre-trained models. Do not provide YAML configuration files.
"""
def __init__(self, model='yolo_nas_s.pt') -> None:
def __init__(self, model="yolo_nas_s.pt") -> None:
"""Initializes the NAS model with the provided or default 'yolo_nas_s.pt' model."""
assert Path(model).suffix not in ('.yaml', '.yml'), 'YOLO-NAS models only support pre-trained models.'
super().__init__(model, task='detect')
assert Path(model).suffix not in (".yaml", ".yml"), "YOLO-NAS models only support pre-trained models."
super().__init__(model, task="detect")
@smart_inference_mode()
def _load(self, weights: str, task: str):
"""Loads an existing NAS model weights or creates a new NAS model with pretrained weights if not provided."""
import super_gradients
suffix = Path(weights).suffix
if suffix == '.pt':
if suffix == ".pt":
self.model = torch.load(weights)
elif suffix == '':
self.model = super_gradients.training.models.get(weights, pretrained_weights='coco')
elif suffix == "":
self.model = super_gradients.training.models.get(weights, pretrained_weights="coco")
# Standardize model
self.model.fuse = lambda verbose=True: self.model
self.model.stride = torch.tensor([32])
@ -65,7 +66,7 @@ class NAS(Model):
self.model.is_fused = lambda: False # for info()
self.model.yaml = {} # for info()
self.model.pt_path = weights # for export()
self.model.task = 'detect' # for export()
self.model.task = "detect" # for export()
def info(self, detailed=False, verbose=True):
"""
@ -80,4 +81,4 @@ class NAS(Model):
@property
def task_map(self):
"""Returns a dictionary mapping tasks to respective predictor and validator classes."""
return {'detect': {'predictor': NASPredictor, 'validator': NASValidator}}
return {"detect": {"predictor": NASPredictor, "validator": NASValidator}}

14
ultralytics/models/nas/predict.py
View file

@ -39,12 +39,14 @@ class NASPredictor(BasePredictor):
boxes = ops.xyxy2xywh(preds_in[0][0])
preds = torch.cat((boxes, preds_in[0][1]), -1).permute(0, 2, 1)
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)
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)

20
ultralytics/models/nas/val.py
View file

@ -5,7 +5,7 @@ import torch
from ultralytics.models.yolo.detect import DetectionValidator
from ultralytics.utils import ops
__all__ = ['NASValidator']
__all__ = ["NASValidator"]
class NASValidator(DetectionValidator):
@ -38,11 +38,13 @@ class NASValidator(DetectionValidator):
"""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,
max_det=self.args.max_det,
max_time_img=0.5)
return ops.non_max_suppression(
preds,
self.args.conf,
self.args.iou,
labels=self.lb,
multi_label=False,
agnostic=self.args.single_cls,
max_det=self.args.max_det,
max_time_img=0.5,
)