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_smcvae(model, data, modalities, n_samples=10, threshold=0.2, ndim=None, verbose=1)[source]ΒΆ

Evaluate the sMCVAE model.

Parameters

model : Module or list of Module

input model.

data : dict

the input data organized by views.

modalities : list of str

names of the model input views.

n_samples : int, default 10

the number of time to sample the posterior.

threshold : float, default 0.2

value for thresholding. If None, no thresholding is applied.

ndim : int, default None

number of dimensions to keep.

verbose : int, default 1

control the verbosity level.

Returns

embeddings : dict

the generated latent representations.

Follow us

© 2023, mmbench developers