def weighted(y_true, y_pred, weights, mask=None):
# score_array has ndim >= 2
score_array = fn(y_true, y_pred)
if mask is not None:
# Cast the mask to floatX to avoid float64 upcasting in theano
mask = K.cast(mask, K.floatX)
# mask should have the same shape as score_array
score_array *= mask
# the loss per batch should be proportional
# to the number of unmasked samples.
score_array /= K.mean(mask)
# reduce score_array to 1D
ndim = K.ndim(score_array)
for _ in range(ndim-1):
score_array = K.mean(score_array, axis=-1)
if weights is not None:
score_array *= weights
return K.mean(score_array)
def weighted(y_true, y_pred, weights, mask=None):
# score_array has ndim >= 2
score_array = fn(y_true, y_pred)
if mask is not None:
# Cast the mask to floatX to avoid float64 upcasting in theano
mask = K.cast(mask, K.floatX)
# mask should have the same shape as score_array
score_array *= mask
# the loss per batch should be proportional
# to the number of unmasked samples.
score_array /= K.mean(mask)
# reduce score_array to 1D
ndim = K.ndim(score_array)
for _ in range(ndim - 1):
score_array = K.mean(score_array, axis=-1)
if weights is not None:
score_array *= weights
return K.mean(score_array)
def output(self, train=False):
X = self.get_input('input')(train)
if self.mode == 'ave':
s = K.mean(X, axis=1)
return s
if self.mode == 'sum':
s = K.sum(X, axis=1)
return s
elif self.mode == 'mul':
s = K.prod(X, axis=1)
return s
else:
raise Exception('Unknown merge mode')
def output(self, train=False):
X = self.get_input('input')(train)
if self.mode == 'ave':
s = K.mean(X, axis=1)
return s
if self.mode == 'sum':
s = K.sum(X, axis=1)
return s
elif self.mode == 'mul':
s = K.prod(X, axis=1)
return s
else:
raise Exception('Unknown merge mode')
def mean_absolute_percentage_error(y_true, y_pred):
diff = K.abs(
(y_true - y_pred) / K.clip(K.abs(y_true), K.epsilon(), np.inf))
return 100. * K.mean(diff, axis=-1)
def mean_absolute_error(y_true, y_pred):
return K.mean(K.abs(y_pred - y_true), axis=-1)
def cosine_proximity(y_true, y_pred):
assert K.ndim(y_true) == 2
assert K.ndim(y_pred) == 2
y_true = K.l2_normalize(y_true, axis=1)
y_pred = K.l2_normalize(y_pred, axis=1)
return -K.mean(y_true * y_pred, axis=1)
def binary_crossentropy(y_true, y_pred):
return K.mean(K.binary_crossentropy(y_pred, y_true), axis=-1)
def hinge(y_true, y_pred):
return K.mean(K.maximum(1. - y_true * y_pred, 0.), axis=-1)
def mean_categorical_crossentropy(y_true, y_pred):
'''Expects a binary class matrix instead of a vector of scalar classes.
'''
return K.mean(K.categorical_crossentropy(y_pred, y_true), axis=-1)
def hinge(y_true, y_pred):
return K.mean(K.maximum(1. - y_true * y_pred, 0.), axis=-1)
def squared_hinge(y_true, y_pred):
return K.mean(K.square(K.maximum(1. - y_true * y_pred, 0.)), axis=-1)
def mean_squared_logarithmic_error(y_true, y_pred):
first_log = K.log(K.clip(y_pred, K.epsilon(), np.inf) + 1.)
second_log = K.log(K.clip(y_true, K.epsilon(), np.inf) + 1.)
return K.mean(K.square(first_log - second_log), axis=-1)
def mean_absolute_percentage_error(y_true, y_pred):
diff = K.abs((y_true - y_pred) / K.clip(K.abs(y_true), K.epsilon(), np.inf))
return 100. * K.mean(diff, axis=-1)
def mean_absolute_error(y_true, y_pred):
return K.mean(K.abs(y_pred - y_true), axis=-1)
def mean_squared_logarithmic_error(y_true, y_pred):
first_log = K.log(K.clip(y_pred, K.epsilon(), np.inf) + 1.)
second_log = K.log(K.clip(y_true, K.epsilon(), np.inf) + 1.)
return K.mean(K.square(first_log - second_log), axis=-1)
def squared_hinge(y_true, y_pred):
return K.mean(K.square(K.maximum(1. - y_true * y_pred, 0.)), axis=-1)
def binary_crossentropy(y_true, y_pred):
return K.mean(K.binary_crossentropy(y_pred, y_true), axis=-1)
def mean_categorical_crossentropy(y_true, y_pred):
'''Expects a binary class matrix instead of a vector of scalar classes.
'''
return K.mean(K.categorical_crossentropy(y_pred, y_true), axis=-1)
def poisson(y_true, y_pred):
return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()), axis=-1)
def poisson(y_true, y_pred):
return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()), axis=-1)
def cosine_proximity(y_true, y_pred):
assert K.ndim(y_true) == 2
assert K.ndim(y_pred) == 2
y_true = K.l2_normalize(y_true, axis=1)
y_pred = K.l2_normalize(y_pred, axis=1)
return -K.mean(y_true * y_pred, axis=1)
def root_mean_squared_error(y_true, y_pred):
return K.sqrt(K.mean(K.square(y_pred - y_true), axis=-1))
def root_mean_squared_error(y_true, y_pred):
return K.sqrt(K.mean(K.square(y_pred - y_true), axis=-1))
