Menu

Benchmark multi-model/multi-view models.

Note

This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the gallery for the big picture.

mmbench.model.eval_models(eval_func, models, data, modalities, **kwargs)[source]ΒΆ

Evaluate N instance of a model.

Parameters

eval_func : callable

the model evaluation function.

models : list of Module

input models.

data : dict

the input data organized by views.

modalities : list of str

name of the views to consider.

kwargs : dict

optional arguments passed to the evaluation function.

Returns

embeddings : dict

the generated latent representations.

Follow us

© 2023, mmbench developers