altametris.sara.core.base_detector¶

Base detector class for inference.

Provides a common interface for running inference on ML models with support for: - Model loading - Batch and single image prediction - Device management - Warmup for performance optimization

Example

>>> class MyDetector(BaseDetector):
...     def _load_model(self, model_path):
...         self.model = torch.load(model_path)
...     def predict(self, source, **kwargs):
...         return self.model(source)

Attributes¶

logger

Classes¶

BaseDetector

Abstract base class for model inference/detection.

Module Contents¶

altametris.sara.core.base_detector.logger¶

class altametris.sara.core.base_detector.BaseDetector(model_path: str | pathlib.Path, device: str = 'auto', warmup: bool = False, **kwargs: Any)¶

Bases: abc.ABC

Abstract base class for model inference/detection.

Provides common inference infrastructure: - Model loading and initialization - Device management - Warmup capability - Prediction interface

Parameters:

model_path – Path to model weights
device – Device for inference (“cpu”, “cuda”, “mps”, “auto”)
warmup – Whether to run warmup inference on initialization

Example

>>> detector = MyDetector(model_path="weights/best.pt", device="cuda")
>>> results = detector.predict(source="image.jpg")

model_path¶

_device¶

model = None¶

_is_initialized = False¶

_resolve_device(device: str) → torch.device¶

Resolve device string to torch.device.

Parameters:: device – Device string
Returns:: Resolved torch.device

property device: torch.device¶: Get current device.

property is_initialized: bool¶: Check if detector is initialized.

abstract _load_model(model_path: pathlib.Path, **kwargs: Any) → None¶

Load model from path.

Parameters:

model_path – Path to model file
**kwargs – Additional loading arguments

Raises:

ModelError – If model cannot be loaded

Note

Must be implemented by subclasses. Should set self.model.

abstract predict(source: Any, **kwargs: Any) → Any¶

Run inference on source.

Parameters:

source – Input source (image path, array, video, etc.)
**kwargs – Inference parameters (conf, iou, etc.)

Returns:

Prediction results (format depends on detector type)

Raises:

InferenceError – If prediction fails

Note

Must be implemented by subclasses

warmup(iterations: int = 3) → None¶

Warmup the model with dummy inference.

Useful for GPU models to pre-allocate memory and compile kernels.

Parameters:: iterations – Number of warmup iterations

Example

>>> detector.warmup(iterations=5)

validate_source(source: Any) → None¶

Validate input source.

Parameters:: source – Input source to validate
Raises:: InferenceError – If source is invalid

__call__(source: Any, **kwargs: Any) → Any¶

Callable interface for prediction.

Parameters:

source – Input source
**kwargs – Inference parameters

Returns:

Prediction results

Example

>>> detector = MyDetector(model_path="weights/best.pt")
>>> results = detector("image.jpg", conf=0.5)

__repr__() → str¶: String representation of detector.