Clarification regarding the data shape illustration about multilabel-timeseries-classification-with-lstm HOT 1 CLOSED

Hi,

[1, time_steps, number_of_features] is correct, where 1 or first dimension represents the batch size or total number of examples. In segments if I remember correctly there was only one feature for each timestep. len(segments) are the total number of examples, which in your example is 1. For example, for an accelerometer signal, we can generate training examples with time steps = 500, number of features = 3 (i.e., 3-axes of accelerometer signal) and the first dimension will simply represent total number of examples. Hope this helps.

from multilabel-timeseries-classification-with-lstm.