anomalib.deploy.inferencers.torch_inferencer

This module contains Torch inference implementations.

Module Contents

Classes

TorchInferencer

PyTorch implementation for the inference.
class anomalib.deploy.inferencers.torch_inferencer.TorchInferencer(config: Union[str, pathlib.Path, omegaconf.DictConfig, omegaconf.ListConfig], model_source: Union[str, pathlib.Path, anomalib.models.components.AnomalyModule], meta_data_path: Union[str, pathlib.Path] = None)[source]

Bases: anomalib.deploy.inferencers.base_inferencer.Inferencer

PyTorch implementation for the inference.

Parameters

  • config (Union[str, Path, DictConfig, ListConfig]) – Configurable parameters that are used during the training stage.

  • model_source (Union[str, Path, AnomalyModule]) – Path to the model ckpt file or the Anomaly model.

  • meta_data_path (Union[str, Path], optional) – Path to metadata file. If none, it tries to load the params from the model state_dict. Defaults to None.

_load_meta_data(path: Optional[Union[str, pathlib.Path]] = None) → Union[Dict, omegaconf.DictConfig][source]

Load metadata from file or from model state dict.

Parameters

path (Optional[Union[str, Path]], optional) – Path to metadata file. If none, it tries to load the params from the model state_dict. Defaults to None.

Returns

Dictionary containing the meta_data.

Return type

Dict

load_model(path: Union[str, pathlib.Path]) → anomalib.models.components.AnomalyModule[source]

Load the PyTorch model.

Parameters

path (Union[str, Path]) – Path to model ckpt file.

Returns

PyTorch Lightning model.

Return type

(AnomalyModule)

pre_process(image: numpy.ndarray) → torch.Tensor[source]

Pre process the input image by applying transformations.

Parameters

image (np.ndarray) – Input image

Returns

pre-processed image.

Return type

Tensor

forward(image: torch.Tensor) → torch.Tensor[source]

Forward-Pass input tensor to the model.

Parameters

image (Tensor) – Input tensor.

Returns

Output predictions.

Return type

Tensor

post_process(predictions: torch.Tensor, meta_data: Optional[Union[Dict, omegaconf.DictConfig]] = None) → Dict[str, Any][source]

Post process the output predictions.

Parameters

  • predictions (Tensor) – Raw output predicted by the model.

  • meta_data (Dict, optional) – Meta data. Post-processing step sometimes requires additional meta data such as image shape. This variable comprises such info. Defaults to None.

Returns

Post processed prediction results.

Return type

Dict[str, Union[str, float, np.ndarray]]