How to reconstruct the decoder from an LSTM-AE? - python-3.x

Question

I have a trained LSTM-AE, of which the architecture is as follows:
In brief, I have an LSTM-AE of depth 3, the number of cells on the LSTM layers on the encoder side are [120, 80, 50] (and symmetric for the decoder). I built the model using the code shown on this page. For information, because I want to train the LSTM-AT directly on variable-length time series, so I didn't specify the timestamps in the input layer, which means the model is trained on batches of size 1 (one time series per batch).
I can extract the encoder just fine, but I cannot do the same for the decoder :-(... My goal is to check, given a vector of 50 features (which are extracted by the encoder), whether the decoder can reconstruct the input series.
Here's my attempt so far:
# load the full autoencoder
model = load_model(path_to_model)
# reconstruct the decoder
in_layer = Input(shape=(None, 50))
time_dist = model.layers[-1]
dec_1 = model.layers[-2]
dec_2 = model.layers[-3]
dec_3 = model.layers[-4]
rep_vec = model.layers[-5]
out_layer = time_dist(dec_1(dec_2(dec_3(rep_vec(in_layer)))))
decoder = Model(in_layer, out_layer, name='decoder')
res = decoder(input_feature) # input_feature has shape (50,)
I obtained this error:
InvalidArgumentError: slice index 1 of dimension 0 out of bounds. [Op:StridedSlice] name: decoder/repeat/strided_slice/
If you are interested in the full error log...
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
Input In [86], in <module>
13 out_layer = time_dist(dec_1(dec_2(dec_3(rep_vec(in_layer)))))
14 decoder = Model(in_layer, out_layer, name='decoder')
---> 15 res = decoder(input_feature)
File ~/venv/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py:1030, in Layer.__call__(self, *args, **kwargs)
1026 inputs = self._maybe_cast_inputs(inputs, input_list)
1028 with autocast_variable.enable_auto_cast_variables(
1029 self._compute_dtype_object):
-> 1030 outputs = call_fn(inputs, *args, **kwargs)
1032 if self._activity_regularizer:
1033 self._handle_activity_regularization(inputs, outputs)
File ~/venv/lib/python3.8/site-packages/tensorflow/python/keras/engine/functional.py:420, in Functional.call(self, inputs, training, mask)
401 #doc_controls.do_not_doc_inheritable
402 def call(self, inputs, training=None, mask=None):
403 """Calls the model on new inputs.
404
405 In this case `call` just reapplies
(...)
418 a list of tensors if there are more than one outputs.
419 """
--> 420 return self._run_internal_graph(
421 inputs, training=training, mask=mask)
File ~/venv/lib/python3.8/site-packages/tensorflow/python/keras/engine/functional.py:556, in Functional._run_internal_graph(self, inputs, training, mask)
553 continue # Node is not computable, try skipping.
555 args, kwargs = node.map_arguments(tensor_dict)
--> 556 outputs = node.layer(*args, **kwargs)
558 # Update tensor_dict.
559 for x_id, y in zip(node.flat_output_ids, nest.flatten(outputs)):
File ~/venv/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py:1030, in Layer.__call__(self, *args, **kwargs)
1026 inputs = self._maybe_cast_inputs(inputs, input_list)
1028 with autocast_variable.enable_auto_cast_variables(
1029 self._compute_dtype_object):
-> 1030 outputs = call_fn(inputs, *args, **kwargs)
1032 if self._activity_regularizer:
1033 self._handle_activity_regularization(inputs, outputs)
File ~/venv/lib/python3.8/site-packages/tensorflow/python/keras/layers/core.py:919, in Lambda.call(self, inputs, mask, training)
915 return var
917 with backprop.GradientTape(watch_accessed_variables=True) as tape,\
918 variable_scope.variable_creator_scope(_variable_creator):
--> 919 result = self.function(inputs, **kwargs)
920 self._check_variables(created_variables, tape.watched_variables())
921 return result
File D:/PhD/Code/feature_learning/train_models/train_lstmae.py:30, in repeat_vector(args)
File ~/venv/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:206, in add_dispatch_support.<locals>.wrapper(*args, **kwargs)
204 """Call target, and fall back on dispatchers if there is a TypeError."""
205 try:
--> 206 return target(*args, **kwargs)
207 except (TypeError, ValueError):
208 # Note: convert_to_eager_tensor currently raises a ValueError, not a
209 # TypeError, when given unexpected types. So we need to catch both.
210 result = dispatch(wrapper, args, kwargs)
File ~/venv/lib/python3.8/site-packages/tensorflow/python/ops/array_ops.py:1040, in _slice_helper(tensor, slice_spec, var)
1038 var_empty = constant([], dtype=dtypes.int32)
1039 packed_begin = packed_end = packed_strides = var_empty
-> 1040 return strided_slice(
1041 tensor,
1042 packed_begin,
1043 packed_end,
1044 packed_strides,
1045 begin_mask=begin_mask,
1046 end_mask=end_mask,
1047 shrink_axis_mask=shrink_axis_mask,
1048 new_axis_mask=new_axis_mask,
1049 ellipsis_mask=ellipsis_mask,
1050 var=var,
1051 name=name)
File ~/venv/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:206, in add_dispatch_support.<locals>.wrapper(*args, **kwargs)
204 """Call target, and fall back on dispatchers if there is a TypeError."""
205 try:
--> 206 return target(*args, **kwargs)
207 except (TypeError, ValueError):
208 # Note: convert_to_eager_tensor currently raises a ValueError, not a
209 # TypeError, when given unexpected types. So we need to catch both.
210 result = dispatch(wrapper, args, kwargs)
File ~/venv/lib/python3.8/site-packages/tensorflow/python/ops/array_ops.py:1213, in strided_slice(input_, begin, end, strides, begin_mask, end_mask, ellipsis_mask, new_axis_mask, shrink_axis_mask, var, name)
1210 if strides is None:
1211 strides = ones_like(begin)
-> 1213 op = gen_array_ops.strided_slice(
1214 input=input_,
1215 begin=begin,
1216 end=end,
1217 strides=strides,
1218 name=name,
1219 begin_mask=begin_mask,
1220 end_mask=end_mask,
1221 ellipsis_mask=ellipsis_mask,
1222 new_axis_mask=new_axis_mask,
1223 shrink_axis_mask=shrink_axis_mask)
1225 parent_name = name
1227 if var is not None:
File ~/venv/lib/python3.8/site-packages/tensorflow/python/ops/gen_array_ops.py:10505, in strided_slice(input, begin, end, strides, begin_mask, end_mask, ellipsis_mask, new_axis_mask, shrink_axis_mask, name)
10503 return _result
10504 except _core._NotOkStatusException as e:
> 10505 _ops.raise_from_not_ok_status(e, name)
10506 except _core._FallbackException:
10507 pass
File ~/venv/lib/python3.8/site-packages/tensorflow/python/framework/ops.py:6897, in raise_from_not_ok_status(e, name)
6895 message = e.message + (" name: " + name if name is not None else "")
6896 # pylint: disable=protected-access
-> 6897 six.raise_from(core._status_to_exception(e.code, message), None)
File <string>:3, in raise_from(value, from_value)
InvalidArgumentError: slice index 1 of dimension 0 out of bounds. [Op:StridedSlice] name: decoder/repeat/strided_slice/
I appreciate very much any advice you would give me!
Edit
Here is the code I used to build the mode:
import tensorflow as tf
from tensorflow.keras.layers import *
from tensorflow.keras.initializers import GlorotUniform
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.backend import shape
def repeat_vector(args):
"""Builds the repeat vector layer dynamically by the size of the input series"""
layer_to_repeat = args[0]
sequence_layer = args[1]
return RepeatVector(shape(sequence_layer)[1])(layer_to_repeat)
n_atts = 3 # time series of 3 measurements
n_units = [120, 80, 50] # encoder - 1st layer: 120, 2nd layer: 80, 3rd layer: 50 (and symmetric for decoder)
n_layers = len(n_units)
init = GlorotUniform(seed=420)
reg = None
optimizer = Adam(learning_rate=0.0001)
activ = 'tanh'
loss_metric = 'mse'
inputs = Input(shape=(None, n_atts), name='input_layer')
# the encoder
encoded = LSTM(n_units[0], name='encoder_1', return_sequences=(n_layers != 1), kernel_initializer=init,
kernel_regularizer=reg, activation=activ)(inputs)
for i in range(1, n_layers):
if i != n_layers - 1:
encoded = LSTM(n_units[i], name='encoder_{}'.format(i + 1), return_sequences=(n_layers != 1),
kernel_initializer=init, kernel_regularizer=reg, activation=activ)(encoded)
else:
encoded = LSTM(n_units[i], name='encoder_{}'.format(i + 1), return_sequences=False,
kernel_initializer=init, kernel_regularizer=reg, activation=activ)(encoded)
# repeat the vector (plug the encoder to the decoder)
repeated = Lambda(repeat_vector, output_shape=(None, n_units[-1]), name='repeat')([encoded, inputs])
# the decoder
decoded = LSTM(n_units[n_layers - 1], return_sequences=True, name='decoder_1',
kernel_initializer=init, kernel_regularizer=reg, activation=activ)(repeated) # first layer
for i in range(1, n_layers):
decoded = LSTM(n_units[n_layers - 1 - i], return_sequences=True, name='decoder_{}'.format(i + 1),
kernel_initializer=init, kernel_regularizer=reg, activation=activ)(decoded)
# last layer
tdist = TimeDistributed(Dense(n_atts))(decoded)
# compile the model
model = Model(inputs, tdist, name='lstm-ae')
model.compile(optimizer=optimizer, loss=loss_metric)
For information, I use tensorflow 2.5.
Because the number of units is read from a config file, I wrote the code this way to add the layers programmatically.