def get_updates(self, loss, params):
grads = self.get_gradients(loss, params)
self.updates = [K.update_add(self.iterations, 1)]
lr = self.lr
if self.initial_decay > 0:
lr *= (1. / (1. + self.decay * K.cast(self.iterations,
K.dtype(self.decay))))
t = K.cast(self.iterations, K.floatx()) + 1
lr_t = lr * (K.sqrt(1. - K.pow(self.beta_2, t)) /
(1. - K.pow(self.beta_1, t)))
ms = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]
vs = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]
self.weights = [self.iterations] + ms + vs
for p, g, m, v in zip(params, grads, ms, vs):
m_t = (self.beta_1 * m) + (1. - self.beta_1) * g
v_t = (self.beta_2 * v) + (1. - self.beta_2) * K.square(g)
p_t = p - lr_t * m_t / (K.sqrt(v_t) + self.epsilon)
self.updates.append(K.update(m, m_t))
self.updates.append(K.update(v, v_t))
new_p = p_t
# Apply constraints.
if getattr(p, 'constraint', None) is not None:
new_p = p.constraint(new_p)
self.updates.append(K.update(p, new_p))
return self.updates
def get_updates(self, loss, params):
grads = self.get_gradients(loss, params)
self.updates = [K.update_add(self.iterations, 1)]
lr = self.lr
if self.initial_decay > 0:
lr *= (1. / (1. + self.decay * K.cast(self.iterations,
K.dtype(self.decay))))
t = K.cast(self.iterations, K.floatx()) + 1
lr_t = lr / (1. - K.pow(self.beta_1, t))
shapes = [K.int_shape(p) for p in params]
# zero init of 1st moment
ms = [K.zeros(shape) for shape in shapes]
# zero init of exponentially weighted infinity norm
us = [K.zeros(shape) for shape in shapes]
self.weights = [self.iterations] + ms + us
for p, g, m, u in zip(params, grads, ms, us):
m_t = (self.beta_1 * m) + (1. - self.beta_1) * g
u_t = K.maximum(self.beta_2 * u, K.abs(g))
p_t = p - lr_t * m_t / (u_t + self.epsilon)
self.updates.append(K.update(m, m_t))
self.updates.append(K.update(u, u_t))
new_p = p_t
# Apply constraints.
if getattr(p, 'constraint', None) is not None:
new_p = p.constraint(new_p)
self.updates.append(K.update(p, new_p))
return self.updates
def get_updates(self, loss, params):
grads = self.get_gradients(loss, params)
shapes = [K.int_shape(p) for p in params]
accumulators = [K.zeros(shape) for shape in shapes]
delta_accumulators = [K.zeros(shape) for shape in shapes]
self.weights = accumulators + delta_accumulators
self.updates = [K.update_add(self.iterations, 1)]
lr = self.lr
if self.initial_decay > 0:
lr *= (1. / (1. + self.decay * K.cast(self.iterations,
K.dtype(self.decay))))
for p, g, a, d_a in zip(params, grads, accumulators, delta_accumulators):
# update accumulator
new_a = self.rho * a + (1. - self.rho) * K.square(g)
self.updates.append(K.update(a, new_a))
# use the new accumulator and the *old* delta_accumulator
update = g * K.sqrt(d_a + self.epsilon) / K.sqrt(new_a + self.epsilon)
new_p = p - lr * update
# Apply constraints.
if getattr(p, 'constraint', None) is not None:
new_p = p.constraint(new_p)
self.updates.append(K.update(p, new_p))
# update delta_accumulator
new_d_a = self.rho * d_a + (1 - self.rho) * K.square(update)
self.updates.append(K.update(d_a, new_d_a))
return self.updates
def get_updates(self, loss, params):
grads = self.get_gradients(loss, params)
self.updates = [K.update_add(self.iterations, 1)]
lr = self.lr
if self.initial_decay > 0:
lr *= (1. / (1. + self.decay * K.cast(self.iterations,
K.dtype(self.decay))))
# momentum
shapes = [K.int_shape(p) for p in params]
moments = [K.zeros(shape) for shape in shapes]
self.weights = [self.iterations] + moments
for p, g, m in zip(params, grads, moments):
v = self.momentum * m - lr * g # velocity
self.updates.append(K.update(m, v))
if self.nesterov:
new_p = p + self.momentum * v - lr * g
else:
new_p = p + v
# Apply constraints.
if getattr(p, 'constraint', None) is not None:
new_p = p.constraint(new_p)
self.updates.append(K.update(p, new_p))
return self.updates
def get_updates(self, loss, params):
grads = self.get_gradients(loss, params)
accumulators = [
K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params
]
self.weights = accumulators
self.updates = [K.update_add(self.iterations, 1)]
lr = self.lr
if self.initial_decay > 0:
lr *= (1. / (1. + self.decay * K.cast(self.iterations,
K.dtype(self.decay))))
for p, g, a in zip(params, grads, accumulators):
# update accumulator
new_a = self.rho * a + (1. - self.rho) * K.square(g)
self.updates.append(K.update(a, new_a))
new_p = p - lr * g / (K.sqrt(new_a) + self.epsilon)
# Apply constraints.
if getattr(p, 'constraint', None) is not None:
new_p = p.constraint(new_p)
self.updates.append(K.update(p, new_p))
return self.updates
def compute_mask(self, inputs, mask=None):
if mask is None:
return None
if not isinstance(mask, list):
raise ValueError('`mask` should be a list.')
if not isinstance(inputs, list):
raise ValueError('`inputs` should be a list.')
if len(mask) != len(inputs):
raise ValueError('The lists `inputs` and `mask` '
'should have the same length.')
if all([m is None for m in mask]):
return None
# Make a list of masks while making sure
# the dimensionality of each mask
# is the same as the corresponding input.
masks = []
for input_i, mask_i in zip(inputs, mask):
if mask_i is None:
# Input is unmasked. Append all 1s to masks,
# but cast it to bool first
masks.append(K.cast(K.ones_like(input_i), 'bool'))
elif K.ndim(mask_i) < K.ndim(input_i):
# Mask is smaller than the input, expand it
masks.append(K.expand_dims(mask_i))
else:
masks.append(mask_i)
concatenated = K.concatenate(masks, axis=self.axis)
return K.all(concatenated, axis=-1, keepdims=False)
def dropped_inputs(inputs=inputs, rate=self.rate, seed=self.seed):
alpha_p = -alpha * scale
kept_idx = K.greater_equal(
K.random_uniform(noise_shape, seed=seed), rate)
kept_idx = K.cast(kept_idx, K.floatx())
a = ((1 - rate) * (1 + rate * alpha_p**2))**-0.5
b = -a * alpha_p * rate
x = inputs * kept_idx + alpha_p * (1 - kept_idx)
return a * x + b
def dropped_inputs(inputs=inputs, rate=self.rate, seed=self.seed):
alpha_p = -alpha * scale
kept_idx = K.greater_equal(K.random_uniform(noise_shape, seed=seed),
rate)
kept_idx = K.cast(kept_idx, K.floatx())
a = ((1 - rate) * (1 + rate * alpha_p ** 2)) ** -0.5
b = -a * alpha_p * rate
x = inputs * kept_idx + alpha_p * (1 - kept_idx)
return a * x + b
def get_updates(self, loss, params):
grads = self.get_gradients(loss, params)
self.updates = [K.update_add(self.iterations, 1)]
t = K.cast(self.iterations, K.floatx()) + 1
# Due to the recommendations in [2], i.e. warming momentum schedule
momentum_cache_t = self.beta_1 * (
1. - 0.5 * (K.pow(K.cast_to_floatx(0.96), t * self.schedule_decay)))
momentum_cache_t_1 = self.beta_1 * (
1. - 0.5 *
(K.pow(K.cast_to_floatx(0.96), (t + 1) * self.schedule_decay)))
m_schedule_new = self.m_schedule * momentum_cache_t
m_schedule_next = self.m_schedule * momentum_cache_t * momentum_cache_t_1
self.updates.append((self.m_schedule, m_schedule_new))
shapes = [K.int_shape(p) for p in params]
ms = [K.zeros(shape) for shape in shapes]
vs = [K.zeros(shape) for shape in shapes]
self.weights = [self.iterations] + ms + vs
for p, g, m, v in zip(params, grads, ms, vs):
# the following equations given in [1]
g_prime = g / (1. - m_schedule_new)
m_t = self.beta_1 * m + (1. - self.beta_1) * g
m_t_prime = m_t / (1. - m_schedule_next)
v_t = self.beta_2 * v + (1. - self.beta_2) * K.square(g)
v_t_prime = v_t / (1. - K.pow(self.beta_2, t))
m_t_bar = (
1. - momentum_cache_t) * g_prime + momentum_cache_t_1 * m_t_prime
self.updates.append(K.update(m, m_t))
self.updates.append(K.update(v, v_t))
p_t = p - self.lr * m_t_bar / (K.sqrt(v_t_prime) + self.epsilon)
new_p = p_t
# Apply constraints.
if getattr(p, 'constraint', None) is not None:
new_p = p.constraint(new_p)
self.updates.append(K.update(p, new_p))
return self.updates
def sparse_top_k_categorical_accuracy(y_true, y_pred, k=5):
return K.mean(K.in_top_k(y_pred, K.cast(K.max(y_true, axis=-1), 'int32'),
k),
axis=-1)
def sparse_categorical_accuracy(y_true, y_pred):
return K.cast(
K.equal(K.max(y_true, axis=-1),
K.cast(K.argmax(y_pred, axis=-1), K.floatx())), K.floatx())
def call(self, inputs):
if K.dtype(inputs) != 'int32':
inputs = K.cast(inputs, 'int32')
out = K.gather(self.embeddings, inputs)
return out
def call(self, inputs):
if K.dtype(inputs) != 'int32':
inputs = K.cast(inputs, 'int32')
out = K.gather(self.embeddings, inputs)
return out
def sparse_categorical_accuracy(y_true, y_pred):
return K.equal(
K.max(y_true, axis=-1), K.cast(K.argmax(y_pred, axis=-1), K.floatx()))
def __call__(self, w):
w *= K.cast(w >= 0., K.floatx())
return w
def call(self, inputs):
boolean_mask = K.any(
K.not_equal(inputs, self.mask_value), axis=-1, keepdims=True)
return inputs * K.cast(boolean_mask, K.floatx())
def iou_accuracy(y_true, y_pred): i = K.cast(K.cumsum(K.maximum(y_true*K.round(y_pred), 0.)), K.floatx()) u = K.cast(K.cumsum(K.maximum(y_true+K.round(y_pred), 0.)), K.floatx()) return i/u
def call(self, inputs):
boolean_mask = K.any(
K.not_equal(inputs, self.mask_value), axis=-1, keepdims=True)
return inputs * K.cast(boolean_mask, K.floatx())
def __call__(self, w): w *= K.cast(w >= 0., K.floatx()) return w
def call(self, inputs, mask=None):
return inputs * K.cast(inputs > self.theta, K.floatx())
def call(self, inputs, mask=None): return inputs * K.cast(inputs > self.theta, K.floatx())
def sparse_top_k_categorical_accuracy(y_true, y_pred, k=5):
return K.mean(K.in_top_k(y_pred,
K.cast(K.max(y_true, axis=-1), 'int32'), k), axis=-1)
