Spaces:
Sleeping
Sleeping
File size: 3,525 Bytes
e1832f4 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
import cv2
import torch
from PIL import Image
from ultralytics.engine.predictor import BasePredictor
from ultralytics.engine.results import Results
from ultralytics.utils import DEFAULT_CFG, ops
class ClassificationPredictor(BasePredictor):
"""
A class extending the BasePredictor class for prediction based on a classification model.
This predictor handles the specific requirements of classification models, including preprocessing images
and postprocessing predictions to generate classification results.
Attributes:
args (dict): Configuration arguments for the predictor.
_legacy_transform_name (str): Name of the legacy transform class for backward compatibility.
Methods:
preprocess: Convert input images to model-compatible format.
postprocess: Process model predictions into Results objects.
Notes:
- Torchvision classification models can also be passed to the 'model' argument, i.e. model='resnet18'.
Examples:
>>> from ultralytics.utils import ASSETS
>>> from ultralytics.models.yolo.classify import ClassificationPredictor
>>> args = dict(model="yolo11n-cls.pt", source=ASSETS)
>>> predictor = ClassificationPredictor(overrides=args)
>>> predictor.predict_cli()
"""
def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
"""Initialize the ClassificationPredictor with the specified configuration and set task to 'classify'."""
super().__init__(cfg, overrides, _callbacks)
self.args.task = "classify"
self._legacy_transform_name = "ultralytics.yolo.data.augment.ToTensor"
def preprocess(self, img):
"""Convert input images to model-compatible tensor format with appropriate normalization."""
if not isinstance(img, torch.Tensor):
is_legacy_transform = any(
self._legacy_transform_name in str(transform) for transform in self.transforms.transforms
)
if is_legacy_transform: # to handle legacy transforms
img = torch.stack([self.transforms(im) for im in img], dim=0)
else:
img = torch.stack(
[self.transforms(Image.fromarray(cv2.cvtColor(im, cv2.COLOR_BGR2RGB))) for im in img], dim=0
)
img = (img if isinstance(img, torch.Tensor) else torch.from_numpy(img)).to(self.model.device)
return img.half() if self.model.fp16 else img.float() # uint8 to fp16/32
def postprocess(self, preds, img, orig_imgs):
"""
Process predictions to return Results objects with classification probabilities.
Args:
preds (torch.Tensor): Raw predictions from the model.
img (torch.Tensor): Input images after preprocessing.
orig_imgs (List[np.ndarray] | torch.Tensor): Original images before preprocessing.
Returns:
(List[Results]): List of Results objects containing classification results for each image.
"""
if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list
orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)
preds = preds[0] if isinstance(preds, (list, tuple)) else preds
return [
Results(orig_img, path=img_path, names=self.model.names, probs=pred)
for pred, orig_img, img_path in zip(preds, orig_imgs, self.batch[0])
]
|