C5_W3: Trigger Word Detection TimeDistributed with Dense layer input shape error

Course Q&A Deep Learning Specialization Sequence Models
1 
 X = TimeDistributed(Dense(1, activation = "sigmoid"))(X)

hits the following error:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-78-282d764c00ab> in <module>
     24 
     25 
---> 26 modelf_test(modelf)

<ipython-input-78-282d764c00ab> in modelf_test(target)
      7     Tx = 5511
      8     n_freq = 101
----> 9     model = target(input_shape = (Tx, n_freq))
     10     expected_model = [['InputLayer', [(None, 5511, 101)], 0],
     11                      ['Conv1D', (None, 1375, 196), 297136, 'valid', 'linear', (4,), (15,), 'GlorotUniform'],

<ipython-input-77-21b8425ab930> in modelf(input_shape)
     47     # Step 4: Time-distributed dense layer (≈1 line)
     48     # TimeDistributed  with sigmoid activation
---> 49     X = TimeDistributed(Dense(1, activation = "sigmoid"))(X)
     50 
     51     ### END CODE HERE ###

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
    924     if _in_functional_construction_mode(self, inputs, args, kwargs, input_list):
    925       return self._functional_construction_call(inputs, args, kwargs,
--> 926                                                 input_list)
    927 
    928     # Maintains info about the `Layer.call` stack.

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in _functional_construction_call(self, inputs, args, kwargs, input_list)
   1096         # Build layer if applicable (if the `build` method has been
   1097         # overridden).
-> 1098         self._maybe_build(inputs)
   1099         cast_inputs = self._maybe_cast_inputs(inputs, input_list)
   1100 

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in _maybe_build(self, inputs)
   2641         # operations.
   2642         with tf_utils.maybe_init_scope(self):
-> 2643           self.build(input_shapes)  # pylint:disable=not-callable
   2644       # We must set also ensure that the layer is marked as built, and the build
   2645       # shape is stored since user defined build functions may not be calling

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/layers/wrappers.py in build(self, input_shape)
    171       raise ValueError(
    172           '`TimeDistributed` Layer should be passed an `input_shape ` '
--> 173           'with at least 3 dimensions, received: ' + str(input_shape))
    174     # Don't enforce the batch or time dimension.
    175     self.input_spec = InputSpec(shape=[None, None] + input_shape[2:])

ValueError: `TimeDistributed` Layer should be passed an `input_shape ` with at least 3 dimensions, received: [None, 128]
2

GRU layer should return sequences!

3

Glad to hear you solved this under your own power. They tried their best to help you out in the comments in the template code:

    # Step 3: Second GRU Layer (≈4 lines)
    # GRU (use 128 units and return the sequences)