Clarification regarding the data shape illustration

[BY-hash]

Hello,
Regarding the illustration of the shape of the data:
"Each training example will be a sequence of shape [1, time_steps, number_of_features]"
However, in the code:
"segments=segments.reshape([len(segments),(win_size + 1),1])"
If I understand correctly, win_size = number_of_features + 1 (because an extra feature of the tims step) and len(segments)=time_steps
So it seems there is a mismatch between the order of dimensions in the illustration and the code

Could you please clearify this issue?
Thank you!

[aqibsaeed]

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.