CODEWITHSUNDEEP
pythondeep-learningkeraskeras-layer
oneThousandHertz
oneThousandHertz

Reputation: 311

Multidimensional Input to Keras LSTM - (for Classification)

I am trying to classify a bunch of spectrograms into C classes using keras' LSTM (with a Dense Layer at the end). To clarify, each spectrogram belongs to a single class from those C classes. Each spectrogram is basically a matrix. It is constructed by taking (lets say, K) measurements at every second for about 1000 seconds. So the matrix has K rows and 1000 columns.

Considering this, how may I specify the shape of this input for the LSTM layer ?

Thank you!

Upvotes: 1

Views: 1534

Answers (1)

lehiester
lehiester

Reputation: 900

It doesn't seem to be in the current documentation for LSTM layers, but input_shape can be provided as (timesteps, input_dim).

If each spectrogram to be classified has 1000 time steps and K measurements at each time step, an LSTM layer can be constructed like this:

LSTM(num_units, input_shape=(1000, K))

Then the shape of the input array for all of the spectrograms should have the shape (num_spectrograms, 1000, K).

Upvotes: 3

Related Questions