mmagic.apis.inferencers.base_mmagic_inferencer

Module Contents

Classes

BaseMMagicInferencer

Base inferencer.

Attributes

InputType
InputsType
PredType
ImgType
ResType

mmagic.apis.inferencers.base_mmagic_inferencer.InputType

mmagic.apis.inferencers.base_mmagic_inferencer.InputsType

mmagic.apis.inferencers.base_mmagic_inferencer.PredType

mmagic.apis.inferencers.base_mmagic_inferencer.ImgType

mmagic.apis.inferencers.base_mmagic_inferencer.ResType

class mmagic.apis.inferencers.base_mmagic_inferencer.BaseMMagicInferencer(config: Union[mmagic.utils.ConfigType, str], ckpt: Optional[str], device: Optional[str] = None, extra_parameters: Optional[Dict] = None, seed: int = 2022, **kwargs)

Bases: mmengine.infer.BaseInferencer

Base inferencer.

Parameters

• config (str or ConfigType) – Model config or the path to it.

• ckpt (str, optional) – Path to the checkpoint.

• device (str, optional) – Device to run inference. If None, the best device will be automatically used.

• extra_parameters (Dict, optional) – Extra parameters for different models in inference stage.

• seed (str, optional) – Seed for inference.

func_kwargs

func_order

extra_parameters

_init_model(cfg: Union[mmagic.utils.ConfigType, str], ckpt: Optional[str], device: str) → None

Initialize the model with the given config and checkpoint on the specific device.

_init_pipeline(cfg: mmagic.utils.ConfigType) → mmengine.dataset.Compose

Initialize the test pipeline.

_init_extra_parameters(extra_parameters: Dict) → None

Initialize extra_parameters of each kind of inferencer.

_update_extra_parameters(**kwargs) → None

update extra_parameters during run time.

_dispatch_kwargs(**kwargs) → Tuple[Dict, Dict, Dict, Dict]

Dispatch kwargs to preprocess(), forward(), visualize() and postprocess() according to the actual demands.

__call__(**kwargs) → Union[Dict, List[Dict]]

Call the inferencer.

Parameters

kwargs – Keyword arguments for the inferencer.

Returns

Results of inference pipeline.

Return type

Union[Dict, List[Dict]]

base_call(**kwargs) → Union[Dict, List[Dict]]

Call the inferencer.

Parameters

kwargs – Keyword arguments for the inferencer.

Returns

Results of inference pipeline.

Return type

Union[Dict, List[Dict]]

get_extra_parameters() → List[str]

Each inferencer may has its own parameters. Call this function to get these parameters.

Returns

List of unique parameters.

Return type

List[str]

postprocess(preds: PredType, imgs: Optional[List[numpy.ndarray]] = None, is_batch: bool = False, get_datasample: bool = False) → Union[ResType, Tuple[ResType, numpy.ndarray]]

Postprocess predictions.

Parameters

• preds (List[Dict]) – Predictions of the model.

• imgs (Optional[np.ndarray]) – Visualized predictions.

• is_batch (bool) – Whether the inputs are in a batch. Defaults to False.

• get_datasample (bool) – Whether to use Datasample to store inference results. If False, dict will be used.

Returns

Inference results as a dict. imgs (torch.Tensor): Image result of inference as a tensor or

tensor list.

Return type

result (Dict)

_pred2dict(pred_tensor: torch.Tensor) → Dict

Extract elements necessary to represent a prediction into a dictionary. It’s better to contain only basic data elements such as strings and numbers in order to guarantee it’s json-serializable.

Parameters

pred_tensor (torch.Tensor) – The tensor to be converted.

Returns

The output dictionary.

Return type

dict

visualize(inputs: list, preds: Any, show: bool = False, result_out_dir: str = '', **kwargs) → List[numpy.ndarray]

Visualize predictions.

Customize your visualization by overriding this method. visualize should return visualization results, which could be np.ndarray or any other objects.

Parameters

• inputs (list) – Inputs preprocessed by _inputs_to_list().

• preds (Any) – Predictions of the model.

• show (bool) – Whether to display the image in a popup window. Defaults to False.

• result_out_dir (str) – Output directory of images. Defaults to ‘’.

Returns

Visualization results.

Return type

List[np.ndarray]