Skip to content

Reference for ultralytics/models/yolo/classify/predict.py

Note

This file is available at https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/classify/predict.py. If you spot a problem please help fix it by contributing a Pull Request 🛠️. Thank you 🙏!


ultralytics.models.yolo.classify.predict.ClassificationPredictor

ClassificationPredictor(cfg=DEFAULT_CFG, overrides=None, _callbacks=None)

Bases: BasePredictor

A class extending the BasePredictor class for prediction based on a classification model.

Notes
  • Torchvision classification models can also be passed to the 'model' argument, i.e. model='resnet18'.
Example
from ultralytics.utils import ASSETS
from ultralytics.models.yolo.classify import ClassificationPredictor

args = dict(model="yolov8n-cls.pt", source=ASSETS)
predictor = ClassificationPredictor(overrides=args)
predictor.predict_cli()
Source code in ultralytics/models/yolo/classify/predict.py
def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
    """Initializes ClassificationPredictor setting the task to 'classify'."""
    super().__init__(cfg, overrides, _callbacks)
    self.args.task = "classify"
    self._legacy_transform_name = "ultralytics.yolo.data.augment.ToTensor"

postprocess

postprocess(preds, img, orig_imgs)

Post-processes predictions to return Results objects.

Source code in ultralytics/models/yolo/classify/predict.py
def postprocess(self, preds, img, orig_imgs):
    """Post-processes predictions to return Results objects."""
    if not isinstance(orig_imgs, list):  # input images are a torch.Tensor, not a list
        orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)

    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])
    ]

preprocess

preprocess(img)

Converts input image to model-compatible data type.

Source code in ultralytics/models/yolo/classify/predict.py
def preprocess(self, img):
    """Converts input image to model-compatible data type."""
    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




📅 Created 11 months ago ✏️ Updated 1 month ago