0
$\begingroup$

I thought that with an LSTM you could use sequences of any length as input, but with shape fixed for each time step, but I encountered an anomalous behavior.

The following code gives the error that I expected, since the input shape is different from the one defined on the LSTM model:

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, LSTM

model = Sequential()
model.add(LSTM(50, input_shape=(None, 15), return_sequences=True))
model.add(Dense(1, activation='linear'))

N_start = 16

inputs = np.zeros((1000, 50, N_start))
model.predict(inputs)

and the error is: ValueError: Input 0 of layer "sequential" is incompatible with the layer: expected shape=(None, None, 15), found shape=(None, 50, 16)

But then, if I use the following code, the model works even at different shapes:

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, LSTM

model = Sequential()
model.add(LSTM(50, input_shape=(None, 15), return_sequences=True))
model.add(Dense(1, activation='linear'))

N_start = 14

inputs = np.zeros((1000, 50, N_start))
add = np.ones((1000, 50, 1))
for i in range(10):
    inputs = np.concatenate((inputs,add), axis = 2)
    print(np.shape(inputs))
    model.predict(inputs)

The output is (1000, 50, 15) 2023-05-17 10:46:19.392818: I tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:428] Loaded cuDNN version 8401 32/32 [==============================] - 2s 6ms/step (1000, 50, 16) 32/32 [==============================] - 0s 6ms/step (1000, 50, 17) 32/32 [==============================] - 0s 6ms/step

I can't understand why it works for inputs with last dimension different from 15.

$\endgroup$
3
  • $\begingroup$ I just tested your second snipped and it fails with error Matrix size-incompatible: In[0]: [32,16], In[1]: [15,200] $\endgroup$
    – noe
    May 17, 2023 at 14:38
  • $\begingroup$ @noe You are right, in one of my devices doesn't work, in another it works (the exact same code). $\endgroup$
    – stopper
    May 17, 2023 at 17:28
  • $\begingroup$ I tested it on Google Colab. $\endgroup$
    – noe
    May 17, 2023 at 20:11

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.