前言
本周使用LSTM创作一首爵士小歌。
代码
djmodel
# GRADED FUNCTION: djmodel
def djmodel(Tx, n_a, n_values):
"""
Implement the model
Arguments:
Tx -- length of the sequence in a corpus
n_a -- the number of activations used in our model
n_values -- number of unique values in the music data
Returns:
model -- a keras model with the
"""
# Define the input of your model with a shape
X = Input(shape=(Tx, n_values))
# Define s0, initial hidden state for the decoder LSTM
a0 = Input(shape=(n_a,), name='a0')
c0 = Input(shape=(n_a,), name='c0')
a = a0
c = c0
### START CODE HERE ###
# Step 1: Create empty list to append the outputs while you iterate (≈1 line)
outputs = []
# Step 2: Loop
for t in range(Tx):
# Step 2.A: select the "t"th time step vector from X.
x = Lambda(lambda x: X[:,t,:])(X)
# Step 2.B: Use reshapor to reshape x to be (1, n_values) (≈1 line)
x = reshapor(x)
# Step 2.C: Perform one step of the LSTM_cell
a, _, c = LSTM_cell(x, initial_state=[a, c])
# Step 2.D: Apply densor to the hidden state output of LSTM_Cell
out = densor(a)
# Step 2.E: add the output to "outputs"
outputs.append(out)
# Step 3: Create model instance
model = Model(inputs=[X,a0,c0],outputs=outputs)
### END CODE HERE ###
return model
music_inference_model
# GRADED FUNCTION: music_inference_model
def music_inference_model(LSTM_cell, densor, n_values = 78, n_a = 64, Ty = 100):
"""
Uses the trained "LSTM_cell" and "densor" from model() to generate a sequence of values.
Arguments:
LSTM_cell -- the trained "LSTM_cell" from model(), Keras layer object
densor -- the trained "densor" from model(), Keras layer object
n_values -- integer, umber of unique values
n_a -- number of units in the LSTM_cell
Ty -- integer, number of time steps to generate
Returns:
inference_model -- Keras model instance
"""
# Define the input of your model with a shape
x0 = Input(shape=(1, n_values))
# Define s0, initial hidden state for the decoder LSTM
a0 = Input(shape=(n_a,), name='a0')
c0 = Input(shape=(n_a,), name='c0')
a = a0
c = c0
x = x0
### START CODE HERE ###
# Step 1: Create an empty list of "outputs" to later store your predicted values (≈1 line)
outputs = []
# Step 2: Loop over Ty and generate a value at every time step
for t in range(Ty):
# Step 2.A: Perform one step of LSTM_cell (≈1 line)
a, _, c = LSTM_cell(x, initial_state=[a, c])
# Step 2.B: Apply Dense layer to the hidden state output of the LSTM_cell (≈1 line)
out = densor(a)
# Step 2.C: Append the prediction "out" to "outputs". out.shape = (None, 78) (≈1 line)
outputs.append(out)
# Step 2.D: Select the next value according to "out", and set "x" to be the one-hot representation of the
# selected value, which will be passed as the input to LSTM_cell on the next step. We have provided
# the line of code you need to do this.
x = Lambda(one_hot)(out)
# Step 3: Create model instance with the correct "inputs" and "outputs" (≈1 line)
inference_model = Model(inputs=[x0,a0,c0],outputs=outputs)
### END CODE HERE ###
return inference_model
predict_and_sample
# GRADED FUNCTION: predict_and_sample
def predict_and_sample(inference_model, x_initializer = x_initializer, a_initializer = a_initializer,
c_initializer = c_initializer):
"""
Predicts the next value of values using the inference model.
Arguments:
inference_model -- Keras model instance for inference time
x_initializer -- numpy array of shape (1, 1, 78), one-hot vector initializing the values generation
a_initializer -- numpy array of shape (1, n_a), initializing the hidden state of the LSTM_cell
c_initializer -- numpy array of shape (1, n_a), initializing the cell state of the LSTM_cel
Returns:
results -- numpy-array of shape (Ty, 78), matrix of one-hot vectors representing the values generated
indices -- numpy-array of shape (Ty, 1), matrix of indices representing the values generated
"""
### START CODE HERE ###
# Step 1: Use your inference model to predict an output sequence given x_initializer, a_initializer and c_initializer.
pred = inference_model.predict([x_initializer,a_initializer,c_initializer])
# Step 2: Convert "pred" into an np.array() of indices with the maximum probabilities
indices = np.argmax(pred, axis = -1)
# Step 3: Convert indices to one-hot vectors, the shape of the results should be (1, )
results = to_categorical(indices,num_classes=78)
### END CODE HERE ###
return results, indices