as_CNN_temp_X: Features (X) data format for a temporal CNN
In stschn/deepANN: Neural Network Toolbox

as_CNN_temp_X

R Documentation

Features (X) data format for a temporal CNN

Description

Features (X) data format for a temporal CNN

Usage

as_CNN_temp_X(x, timesteps = 1L, subsequences = NULL)

Arguments

`x`	A feature data set, usually a matrix or data frame, returned by `get_LSTM_XY`.
`timesteps`	Number of timesteps; stands for the number of different periods within one sample (record) of the result, the resampled feature matrix `x`. If `subsequences` is given, `timesteps` is divided by `subsequences` to spawn the overall timesteps range (origin timesteps) within the result.
`subsequences`	Number of subsequences within the outcome tensor. Using a CNN without RNN layers like LSTM layers, the number of subsequences is `NULL` (default). Otherwise, this number must be an integer multiple of `timesteps` to keep the origin timesteps value. To avoid problems in this regard, using a value of `1` is a proper solution.

Value

A 3D-array with dimensions samples, timesteps and features or a 4D-array with dimensions samples, subsequences, timesteps and features.

Other Convolutional Neural Network (CNN): alexnet(), as_CNN_image_X(), as_CNN_image_Y(), as_CNN_temp_Y(), as_images_array(), as_images_tensor(), images_load(), images_resize(), inception_resnet_v2(), inception_v3(), lenet5(), mobilenet(), mobilenet_v2(), mobilenet_v3(), nasnet(), resnet, unet(), vgg, xception(), zfnet()