def kullback_leibler_divergence(y_true, y_pred):
'''Calculates the Kullback-Leibler (KL) divergence between prediction
and target values.
'''
y_true = K.clip(y_true, K.epsilon(), 1)
y_pred = K.clip(y_pred, K.epsilon(), 1)
return K.sum(y_true * K.log(y_true / y_pred), axis=-1)
def fbeta_score(y_true, y_pred, beta=1):
'''Calculates the F score, the weighted harmonic mean of precision and recall.
This is useful for multi-label classification, where input samples can be
classified as sets of labels. By only using accuracy (precision) a model
would achieve a perfect score by simply assigning every class to every
input. In order to avoid this, a metric should penalize incorrect class
assignments as well (recall). The F-beta score (ranged from 0.0 to 1.0)
computes this, as a weighted mean of the proportion of correct class
assignments vs. the proportion of incorrect class assignments.
With beta = 1, this is equivalent to a F-measure. With beta < 1, assigning
correct classes becomes more important, and with beta > 1 the metric is
instead weighted towards penalizing incorrect class assignments.
'''
if beta < 0:
raise ValueError('The lowest choosable beta is zero (only precision).')
# If there are no true positives, fix the F score at 0 like sklearn.
if K.sum(K.round(K.clip(y_true, 0, 1))) == 0:
return 0
p = precision(y_true, y_pred)
r = recall(y_true, y_pred)
bb = beta**2
fbeta_score = (1 + bb) * (p * r) / (bb * p + r + K.epsilon())
return fbeta_score
def recall(y_true, y_pred):
'''Calculates the recall, a metric for multi-label classification of
how many relevant items are selected.
'''
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
recall = true_positives / (possible_positives + K.epsilon())
return recall
def precision(y_true, y_pred):
'''Calculates the precision, a metric for multi-label classification of
how many selected items are relevant.
'''
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
precision = true_positives / (predicted_positives + K.epsilon())
return precision
def matthews_correlation(y_true, y_pred):
'''Calculates the Matthews correlation coefficient measure for quality
of binary classification problems.
'''
y_pred_pos = K.round(K.clip(y_pred, 0, 1))
y_pred_neg = 1 - y_pred_pos
y_pos = K.round(K.clip(y_true, 0, 1))
y_neg = 1 - y_pos
tp = K.sum(y_pos * y_pred_pos)
tn = K.sum(y_neg * y_pred_neg)
fp = K.sum(y_neg * y_pred_pos)
fn = K.sum(y_pos * y_pred_neg)
numerator = (tp * tn - fp * fn)
denominator = K.sqrt((tp + fp) * (tp + fn) * (tn + fp) * (tn + fn))
return numerator / (denominator + K.epsilon())
def create_model():
tokens = get_tokens()
num_tokens = len(tokens) + 1
input_data = Input(name='speech_data_input', shape=(500, 13))
layer_dense_1 = Dense(256, activation="relu", use_bias=True, kernel_initializer='he_normal')(input_data)
layer_dropout_1 = Dropout(0.4)(layer_dense_1)
layer_dense_2 = Dense(512, activation="relu", use_bias=True, kernel_initializer='he_normal')(layer_dropout_1)
layer_gru1 = GRU(512, return_sequences=True, kernel_initializer='he_normal', dropout=0.4)(layer_dense_2)
layer_gru2 = GRU(512, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', dropout=0.4)(layer_gru1)
layer_dense_3 = Dense(256, activation="relu", use_bias=True, kernel_initializer='he_normal')(layer_gru2)
layer_dropout_2 = Dropout(0.4)(layer_dense_3)
layer_dense_4 = Dense(num_tokens, activation="relu", use_bias=True, kernel_initializer='he_normal')(layer_dropout_2)
output = Activation('softmax', name='Activation0')(layer_dense_4)
#ctc
labels = Input(name='speech_labels', shape=[70], dtype='int64')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
loss_out = Lambda(ctc_lambda, output_shape=(1,), name='ctc')([labels, output, input_length, label_length])
model = Model(inputs=[input_data, labels, input_length, label_length], outputs=loss_out)
adad = Adadelta(lr=0.01, rho=0.95, epsilon=K.epsilon())
model.compile(loss={'ctc': lambda y_true, output: output}, optimizer=adad)
print("model compiled successful!")
return model
