# Defined shared layers as global variables
repeator = RepeatVector(Tx) #<Gema> Repeats the input Tx times.
concatenator = Concatenate(axis=-1) #<Gema> Layer that concatenates a list of inputs. axis: Axis along which to concatenate, in this case, on the last axis.
densor1 = Dense(10, activation = "tanh") #<Gema> Just your regular densely-connected NN layer.#<Gema> Dense implements the operation: output = activation(dot(input, kernel) + bias) where kernel is a weights matrix created by the layer
densor2 = Dense(1, activation = "relu")
activator = Activation(softmax, name='attention_weights') # We are using a custom softmax(axis = 1) loaded in this notebook#<Gema> Applies an activation function to an output.
dotor = Dot(axes = 1)
#<Gema> Layer that computes a dot product between samples in two tensors.defone_step_attention(a, s_prev):
"""
Performs one step of attention: Outputs a context vector computed as a dot product of the attention weights
"alphas" and the hidden states "a" of the Bi-LSTM.
Arguments:
a -- hidden state output of the Bi-LSTM, numpy-array of shape (m, Tx, 2*n_a)
s_prev -- previous hidden state of the (post-attention) LSTM, numpy-array of shape (m, n_s)
Returns:
context -- context vector, input of the next (post-attetion) LSTM cell
"""### START CODE HERE #### Use repeator to repeat s_prev to be of shape (m, Tx, n_s) so that you can concatenate it with all hidden states "a" (≈ 1 line)
s_prev = repeator(s_prev)
# Use concatenator to concatenate a and s_prev on the last axis (≈ 1 line)
concat = concatenator([a,s_prev])
# Use densor1 to propagate concat through a small fully-connected neural network to compute the "intermediate energies" variable e. (≈1 lines)
e = densor1(concat)
# Use densor2 to propagate e through a small fully-connected neural network to compute the "energies" variable energies. (≈1 lines)
energies = densor2(e)
# Use "activator" on "energies" to compute the attention weights "alphas" (≈ 1 line)
alphas = activator(energies)
# Use dotor together with "alphas" and "a" to compute the context vector to be given to the next (post-attention) LSTM-cell (≈ 1 line)
context = dotor([alphas,a])
### END CODE HERE ###return context
