format_activations: Format filter activations for plotting.

Description Usage Arguments Value Author(s)

Description

Format the first-layer filter activations for plotting with plot_filter_activations_byClass.

Usage

1
2
format_activations(model, data, y, input_layer = 1, output_layer,
  buffer = 0, motif.names)

Arguments

model

A Keras model.

data

Data array returned from one_hot to obtain activations for.

y

Vector of class labels.

input_layer

Integer value denoting the input data. If NULL, assumes a single input layer.

output_layer

Integer denoting output layer or string containing the layer name.

buffer

Where to start extracting the beta coefficients from.

motif.names

Array containing names for the filters.

Value

Tibble of formatted activations.

Author(s)

Matthew Ploenzke, ploenzke@g.harvard.edu


mPloenzke/learnMotifs documentation built on May 27, 2019, 11:55 a.m.