Inserting an LSTM layer raises a shape error about nengo-dl HOT 3 CLOSED

If you use h = nengo_dl.Layer(tf.keras.layers.LSTM(units=128))(inp, shape_in=(n_steps, d)) that should work (where n_steps is the number of timesteps in your data and d is the dimensionality of the data on each timestep).

from nengo-dl.

Thanks. Got this to work with the following code:

with nengo.Network(seed=seed) as net:
    nengo_dl.configure_settings(
        trainable=None, stateful=False, keep_history=False,
    )
   
    inp = nengo.Node(np.zeros(np.prod(train_images.shape[1:])))

    h = nengo_dl.Layer(tf.keras.layers.LSTM(units=128))(
        inp, shape_in=(train_images.shape[1], 1))

    out = nengo_dl.Layer(tf.keras.layers.Dense(units=10))(h)
    p = nengo.Probe(out)

and using train_images.reshape((train_images.shape[0], 1, -1)) in place of train_images where passed to sim. Note this passes the entire sequence in one step, rather than the usual Nengo approach of iterating across each time-step in the simulation.

from nengo-dl.

Marking this as resolved since the fix above works!

from nengo-dl.