def mn(weights, name=None):
"""Applies max-norm regularization to weights."""
try: # TF12
with ops.name_scope(scope, 'maxnorm_regularizer', [weights]) as name:
my_scale = ops.convert_to_tensor(scale,
dtype=weights.dtype.base_dtype,
name='scale')
return standard_ops.mul(my_scale, standard_ops.reduce_max(standard_ops.abs(weights)), name=scope)
except: # TF11
with ops.op_scope([weights], name, 'maxnorm_regularizer') as scope:
my_scale = ops.convert_to_tensor(scale,
dtype=weights.dtype.base_dtype,
name='scale')
return standard_ops.mul(my_scale, standard_ops.reduce_max(standard_ops.abs(weights)), name=scope)
def mn(weights, name=None):
"""Applies max-norm regularization to weights."""
with ops.op_scope([weights], name, 'maxnorm_regularizer') as scope:
my_scale = ops.convert_to_tensor(scale,
dtype=weights.dtype.base_dtype,
name='scale')
return standard_ops.mul(my_scale, standard_ops.reduce_max(standard_ops.abs(weights)), name=scope)
def mn(weights, name='max_regularizer'):
"""Applies max-norm regularization to weights."""
with tf.name_scope(name) as scope:
my_scale = ops.convert_to_tensor(scale, dtype=weights.dtype.base_dtype, name='scale')
# if tf.__version__ <= '0.12':
# standard_ops_fn = standard_ops.mul
# else:
standard_ops_fn = standard_ops.multiply
return standard_ops_fn(my_scale, standard_ops.reduce_max(standard_ops.abs(weights)), name=scope)
def mn(weights, name='max_regularizer'):
"""Applies max-norm regularization to weights."""
with tf.name_scope(name) as scope:
my_scale = ops.convert_to_tensor(scale, dtype=weights.dtype.base_dtype, name='scale')
# if tf.__version__ <= '0.12':
# standard_ops_fn = standard_ops.mul
# else:
standard_ops_fn = standard_ops.multiply
return standard_ops_fn(my_scale, standard_ops.reduce_max(standard_ops.abs(weights)), name=scope)
def l1(weights, name=None):
"""Applies L1 regularization to weights."""
with ops.name_scope(scope, 'l1_regularizer', [weights]) as name:
my_scale = ops.convert_to_tensor(scale,
dtype=weights.dtype.base_dtype,
name='scale')
return standard_ops.mul(
my_scale,
standard_ops.reduce_sum(standard_ops.abs(weights)),
name=name)
def mn_i(weights, name=None):
"""Applies max-norm regularization to weights."""
with ops.op_scope([weights], name, 'maxnorm_o_regularizer') as scope:
my_scale = ops.convert_to_tensor(scale,
dtype=weights.dtype.base_dtype,
name='scale')
return standard_ops.mul(my_scale,
standard_ops.reduce_sum(
standard_ops.reduce_max(
standard_ops.abs(weights), 1)),
name=scope)
def _distribution(self, state):
distribution = _maximal_eigenvector_power_method(
self._stochastic_matrix(state))
distribution = standard_ops.abs(distribution)
distribution /= standard_ops.reduce_sum(distribution)
return distribution
def _distribution(self, state):
distribution = _maximal_eigenvector_power_method(
self._stochastic_matrix(state))
distribution = standard_ops.abs(distribution)
distribution /= standard_ops.reduce_sum(distribution)
return distribution
def l1(weights, name=None):
"""Applies L1 regularization to weights."""
with ops.op_scope([weights], name, "l1_regularizer") as scope:
my_scale = ops.convert_to_tensor(scale, dtype=weights.dtype.base_dtype, name="scale")
return standard_ops.mul(my_scale, standard_ops.reduce_sum(standard_ops.abs(weights)), name=scope)
