autoencoder.fit() raises 'KeyError: 'Exception encountered when calling Functional.call()'

[albas99]

I'm trying to build a stacked LSTM sequence auto-encoder that takes a signal of 430 timesteps with each timestep having 1 value. You can see the code for the model below:

feat_dim = 1
timesteps = 430
inputs = keras.Input(shape = (timesteps, feat_dim), dtype = 'float32')
x = layers.LSTM(320, activation = 'relu', return_sequences = True)(inputs)
x = layers.LSTM(256, activation = 'relu', return_sequences = True)(x)
x = layers.LSTM(128, activation = 'relu', return_sequences = True)(x)
x = layers.LSTM(64, activation = 'relu', return_sequences = True)(x)
x = layers.LSTM(32, activation = 'relu', return_sequences = True)(x)
x = layers.LSTM(16, activation = 'relu', return_sequences = True)(x)
encoded = layers.LSTM(encoding_dim, activation = 'relu', return_sequences = False)(x)

x = layers.RepeatVector(timesteps)(encoded)
x = layers.LSTM(16, activation = 'relu', return_sequences = True)(x)
x = layers.LSTM(32, activation = 'relu', return_sequences = True)(x)
x = layers.LSTM(64, activation = 'relu', return_sequences = True)(x)
x = layers.LSTM(128, activation = 'relu', return_sequences = True)(x)
x = layers.LSTM(256, activation = 'relu', return_sequences = True)(x)
x = layers.LSTM(320, activation = 'relu', return_sequences = True)(x)
decoded = layers.TimeDistributed(layers.Dense(feat_dim, activation = 'sigmoid'))(x)

autoencoder = keras.Model(input_dim, decoded)
encoder = keras.Model(input_dim, encoded)
encoded_input = keras.Input(shape=(timesteps, encoding_dim,))
decoded_layer = autoencoder.layers[-7](encoded_input)
decoded_layer = autoencoder.layers[-6](decoded_layer)
decoded_layer = autoencoder.layers[-5](decoded_layer)
decoded_layer = autoencoder.layers[-4](decoded_layer)
decoded_layer = autoencoder.layers[-3](decoded_layer)
# decoded_layer = autoencoder.layers[-2](decoded_layer)
decoded_layer = autoencoder.layers[-1](decoded_layer)
decoder = keras.Model(encoded_input, decoded)
autoencoder.compile(optimizer = 'adam', loss = 'mean_squared_error')

autoencoder.fit(xtrainsc, xtrainsc,
               epochs = 50,
               batch_size = 128,
               shuffle = True,
               validation_data = (xtestsc, xtestsc))

When I run autoencoder.summary() I get the model summary just fine but when I run autoencoder.fit() I get the following error:

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-136-aff0d412291f> in <cell line: 1>()
----> 1 autoencoder.fit(xtrainsc, xtrainsc,
      2                epochs = 50,
      3                batch_size = 128,
      4                shuffle = True,
      5                validation_data = (xtestsc, xtestsc))

/usr/local/lib/python3.10/dist-packages/keras/src/utils/traceback_utils.py in error_handler(*args, **kwargs)
    120             # To get the full stack trace, call:
    121             # `keras.config.disable_traceback_filtering()`
--> 122             raise e.with_traceback(filtered_tb) from None
    123         finally:
    124             del filtered_tb

/usr/local/lib/python3.10/dist-packages/keras/src/ops/function.py in _run_through_graph(self, inputs, operation_fn, call_fn)
    177         output_tensors = []
    178         for x in self.outputs:
--> 179             output_tensors.append(tensor_dict[id(x)])
    180 
    181         return tree.pack_sequence_as(self._outputs_struct, output_tensors)

KeyError: 'Exception encountered when calling Functional.call().\n\n\x1b[1m139922652929696\x1b[0m\n\nArguments received by Functional.call():\n  • inputs=tf.Tensor(shape=(None, 430, 1), dtype=float32)\n  • training=True\n  • mask=None'

I've reshaped my dataset already to (batch, timesteps, feature) and when I try the code below adapted from the original keras tutorial on building autoencoders, it works, just that the train and validation loss start giving NaN values after a number of epochs.

encoded = layers.LSTM(encoding_dim, activation = 'relu')(inputs)
x = layers.RepeatVector(timesteps)(encoded)
decoded = layers.LSTM(encoding_dim, activation = 'relu', return_sequences = True)(x)
decoded = layers.TimeDistributed(layers.Dense(feat_dim, activation = 'sigmoid'))(decoded)

autoencoder = keras.Model(inputs, decoded)
encoder = keras.Model(inputs, encoded)
encoded_input = keras.Input(shape=(timesteps, encoding_dim))
decoder = keras.Model(encoded_input, decoded)

Has anyone encountered a similar error and fixed it? I'd love to get some help on this. Thanks in advance.

[mehtamansi29]

Hi @albas99 -

Thanks for reporting the issue. Here in your code some values like encoding_dim, xtrainsc and xtestsc is missing.
I took sample values for encoding_dim, xtrainsc and xtestsc to run your code.

encoding_dim=16
xtrainsc = np.random.rand(100, timesteps, feat_dim).astype('float32')
xtestsc = np.random.rand(20, timesteps, feat_dim).astype('float32')

Also while creating autoencoder and encoder, for input argument you have define input_dim instead of inputs defined previously. Same mentioned in Sequence-to-sequence autoencoder here.

Changing this

autoencoder = keras.Model(input_dim, decoded)
encoder = keras.Model(input_dim, encoded)

to

autoencoder = keras.Model(inputs, decoded)
encoder = keras.Model(inputs, encoded)

Attached gist here for reference.
Kindly try to run attached gist code with your data and let me know if issue persists.

[albas99]

Thank for the response @mehtamansi29 , yeah the issue turned out to be not replacing input_dim with inputs, I was using MLPs before so when so the input_dim variable had a different meaning from the inputs. I had the encoding_dim, xtrainsc and xtestsc, I just forgot to add it to the code above in my question.

[mehtamansi29]

Hi @albas99 - Thanks. As issue is resolved then this issue. If anything more related to this issue then feel free to reopen this issue.

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No