mmagic.apis.inferencers.conditional_inferencer
¶
Module Contents¶
Classes¶
inferencer that predicts with conditional models. |
- class mmagic.apis.inferencers.conditional_inferencer.ConditionalInferencer(config: Union[mmagic.utils.ConfigType, str], ckpt: Optional[str], device: Optional[str] = None, extra_parameters: Optional[Dict] = None, seed: int = 2022, **kwargs)[source]¶
Bases:
mmagic.apis.inferencers.base_mmagic_inferencer.BaseMMagicInferencer
inferencer that predicts with conditional models.
- preprocess(label: mmagic.apis.inferencers.base_mmagic_inferencer.InputsType) Dict [source]¶
Process the inputs into a model-feedable format.
- Parameters
label (InputsType) – Input label for condition models.
- Returns
Results of preprocess.
- Return type
results(Dict)
- forward(inputs: mmagic.apis.inferencers.base_mmagic_inferencer.InputsType) mmagic.apis.inferencers.base_mmagic_inferencer.PredType [source]¶
Forward the inputs to the model.
- visualize(preds: mmagic.apis.inferencers.base_mmagic_inferencer.PredType, result_out_dir: str = None) List[numpy.ndarray] [source]¶
Visualize predictions.
- Parameters
preds (List[Union[str, np.ndarray]]) – Forward results by the inferencer.
data (List[Dict]) – Not needed by this kind of inferencer.
result_out_dir (str) – Output directory of image. Defaults to ‘’.
- Returns
Result of visualize
- Return type
List[np.ndarray]
- _pred2dict(data_sample: mmagic.structures.DataSample) Dict [source]¶
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
data_sample (DataSample) – The data sample to be converted.
- Returns
The output dictionary.
- Return type
dict