reshape_input: Replace input layer

In GenomeNet/deepG: Deep Learning for Genome Sequence Data

Replace input layer

Description

Replace first layer of model with new input layer of different shape. Only works for sequential models that use CNN and LSTM layers.

Usage

reshape_input(model, input_shape)

Arguments

model	A keras model.
input_shape	The new input shape vector (without batch size).

Value

A keras model with changed input shape of input model.

Examples

model_1 <-  create_model_lstm_cnn(
  maxlen = 50,
  kernel_size = c(10, 10),
  filters = c(64, 128),
  pool_size = c(2, 2),
  layer_lstm = c(32),
  verbose = FALSE,
  layer_dense = c(64, 2))
model <- reshape_input(model_1, input_shape = c(120, 4))
model

GenomeNet/deepG documentation built on Dec. 24, 2024, 12:11 p.m.