Data Science Asked on June 14, 2021
I have a small data set with the transformed series vector data with the music genre. The goal for me is to use the LSTM model to learn the non-linear pattern each row for genre classification. The LSTM model is one of the most suitable models for doing this task.
So, my original data set look like this:
vec_1,vec_2,...,vec30,genre
50 30 0 pop
.
.
.
The shape of the training data is (7678,30), so, at first, I just randomly reshape the training data such as (7678,2,15) to fit the input requirement (samples, time steps, features) for the LSTM model.
However, I am confused about the input data, since the time series data I’ve seen so far, from many tutorials is like:
time,vec_1,vec_2
0 50 30
1 . .
. . .
. . .
. . .
Should I transpose the matrix before I fit in the LSTM model like this?
0 1 2 3 . . . 7678
vec_1 50
vec_2 30
.
.
.
vec_30 0
genre pop
The shape of this data will be (30,7678), and it looks right to fit in the LSTM model.
If so, when I reshape it to (7678,2,15), does it mean the same before I transpose the matrix? meaning that with 7678 samples, with 2 timesteps, with 15 features.
Get help from others!
Recent Answers
Recent Questions
© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP