emmi_inference.common¶

Classes¶

`SaveFormat`	Supported on-disk formats for tensor outputs.
`DictMode`	How to persist mapping outputs.

Sanitize a suffix for safe filesystem usage.

class emmi_inference.common.SaveFormat¶

Bases: str, enum.Enum

Supported on-disk formats for tensor outputs.

Values:: PYTORCH_PT: PyTorch serialized tensor/map (.pt). PYTORCH_TH: Alias, normalized to .pt. PYTORCH_PTH: Alias, normalized to .pt. NUMPY_NPY: NumPy array (.npy) for single tensors. NUMPY_NPZ: Compressed NumPy archive (.npz) for mappings.

Initialize self. See help(type(self)) for accurate signature.

classmethod normalize(save_format)¶

Return the canonical save format.

Parameters:: save_format (SaveFormat) – A concrete SaveFormat.
Returns:: PYTORCH_PT when given PYTORCH_TH/PYTORCH_PTH, otherwise the input value.
Return type:: SaveFormat

class emmi_inference.common.DictMode¶

Bases: str, enum.Enum

How to persist mapping outputs.

Values:: SPLIT: Write one file per key (suffix _key appended to the stem). SINGLE: Write a single container file containing all key/value pairs.

Initialize self. See help(type(self)) for accurate signature.

emmi_inference.common.sanitize_suffix(suffix)¶

Sanitize a suffix for safe filesystem usage.

Replaces characters outside [A-Za-z0-9_-] with _.