oumi.core.models

Core models module for the Oumi (Open Universal Machine Intelligence) library.

This module provides base classes for different types of models used in the Oumi framework.

See also

• oumi.models: Module containing specific model implementations.

• oumi.models.mlp.MLPEncoder: An example of a concrete model

  implementation.

Example

To create a custom model, inherit from BaseModel:

>>> from oumi.core.models import BaseModel
>>> class CustomModel(BaseModel):
...     def __init__(self, *args, **kwargs):
...         super().__init__(*args, **kwargs)
...
...     def forward(self, x):
...         # Implement the forward pass
...         pass

class oumi.core.models.BaseModel(**kwargs)

Bases: Module, ABC

abstract property criterion: Callable

Returns the criterion function used for model training.

Returns:

A callable object representing the criterion function.

abstract forward(**kwargs) → dict[str, Tensor]

Performs the forward pass of the model.

Optionally computes the loss if the necessary keyword arguments are provided.

Parameters:

• **kwargs – should contain all the parameters needed

• pass (to perform the forward)

• needed. (and compute the loss if)

Returns:

A dictionary containing the output tensors.