def compute_gradients(self,
loss,
var_list=None,
gate_gradients=optimizer.Optimizer.GATE_OP,
aggregation_method=None,
colocate_gradients_with_ops=False,
grad_loss=None):
"""Compute gradients of `loss` for the variables in `var_list`.
Add rho*elastic_difference to loss to control the exploration
This is the first part of `minimize()`. It returns a list
of (gradient, variable) pairs where "gradient" is the gradient
for "variable". Note that "gradient" can be a `Tensor`, an
`IndexedSlices`, or `None` if there is no gradient for the
given variable.
Args:
loss: A Tensor containing the value to minimize.
var_list: Optional list or tuple of `tf.Variable` to update to minimize
`loss`. Defaults to the list of variables collected in the graph
under the key `GraphKey.TRAINABLE_VARIABLES`.
gate_gradients: How to gate the computation of gradients. Can be
`GATE_NONE`, `GATE_OP`, or `GATE_GRAPH`.
aggregation_method: Specifies the method used to combine gradient terms.
Valid values are defined in the class `AggregationMethod`.
colocate_gradients_with_ops: If True, try colocating gradients with
the corresponding op.
grad_loss: Optional. A `Tensor` holding the gradient computed for `loss`.
Returns:
A list of (gradient, variable) pairs. Variable is always present, but
gradient can be `None`.
Raises:
TypeError: If `var_list` contains anything else than `Variable` objects.
ValueError: If some arguments are invalid.
"""
if not var_list:
var_list = variables.trainable_variables()
elastic_difference = [
math_ops.subtract(v, lv)
for v, lv in zip(variables.trainable_variables(),
[self._local_map[var] for var in var_list])
]
distance_loss = self._rho * math_ops.add_n(
[gen_nn_ops.l2_loss(ed) for ed in elastic_difference])
total_loss = loss + distance_loss
return self._opt.compute_gradients(total_loss, var_list,
gate_gradients, aggregation_method,
colocate_gradients_with_ops,
grad_loss)
def compute_gradients(self,
loss,
var_list=None,
gate_gradients=optimizer.Optimizer.GATE_OP,
aggregation_method=None,
colocate_gradients_with_ops=False,
grad_loss=None):
"""Compute gradients of `loss` for the variables in `var_list`.
Add rho*elastic_difference to loss to control the exploration
This is the first part of `minimize()`. It returns a list
of (gradient, variable) pairs where "gradient" is the gradient
for "variable". Note that "gradient" can be a `Tensor`, an
`IndexedSlices`, or `None` if there is no gradient for the
given variable.
Args:
loss: A Tensor containing the value to minimize.
var_list: Optional list or tuple of `tf.Variable` to update to minimize
`loss`. Defaults to the list of variables collected in the graph under
the key `GraphKey.TRAINABLE_VARIABLES`.
gate_gradients: How to gate the computation of gradients. Can be
`GATE_NONE`, `GATE_OP`, or `GATE_GRAPH`.
aggregation_method: Specifies the method used to combine gradient terms.
Valid values are defined in the class `AggregationMethod`.
colocate_gradients_with_ops: If True, try colocating gradients with the
corresponding op.
grad_loss: Optional. A `Tensor` holding the gradient computed for `loss`.
Returns:
A list of (gradient, variable) pairs. Variable is always present, but
gradient can be `None`.
Raises:
TypeError: If `var_list` contains anything else than `Variable` objects.
ValueError: If some arguments are invalid.
"""
if not var_list:
var_list = variables.trainable_variables()
elastic_difference = [
math_ops.subtract(v, lv)
for v, lv in zip(variables.trainable_variables(),
[self._local_map[var] for var in var_list])
]
distance_loss = self._rho * math_ops.add_n(
[gen_nn_ops.l2_loss(ed) for ed in elastic_difference])
total_loss = loss + distance_loss
return self._opt.compute_gradients(total_loss, var_list, gate_gradients,
aggregation_method,
colocate_gradients_with_ops, grad_loss)
def global_norm(t_list, name=None):
"""Computes the global norm of multiple tensors.
Given a tuple or list of tensors `t_list`, this operation returns the
global norm of the elements in all tensors in `t_list`. The global norm is
computed as:
`global_norm = sqrt(sum([l2norm(t)**2 for t in t_list]))`
Any entries in `t_list` that are of type None are ignored.
Args:
t_list: A tuple or list of mixed `Tensors`, `IndexedSlices`, or None.
name: A name for the operation (optional).
Returns:
A 0-D (scalar) `Tensor` of type `float`.
Raises:
TypeError: If `t_list` is not a sequence.
"""
if (not isinstance(t_list, collections_abc.Sequence)
or isinstance(t_list, six.string_types)):
raise TypeError("`t_list` should be a sequence of tensors. Received "
f"{type(t_list)}.")
t_list = list(t_list)
with ops.name_scope(name, "global_norm", t_list) as name:
values = [
ops.convert_to_tensor(
t.values if isinstance(t, ops.IndexedSlices) else t,
name="t_%d" % i) if t is not None else t
for i, t in enumerate(t_list)
]
half_squared_norms = []
for v in values:
if v is not None:
with ops.colocate_with(v):
half_squared_norms.append(gen_nn_ops.l2_loss(v))
half_squared_norm = math_ops.reduce_sum(
array_ops.stack(half_squared_norms))
norm = math_ops.sqrt(
half_squared_norm *
constant_op.constant(2.0, dtype=half_squared_norm.dtype),
name="global_norm")
return norm
def global_norm(t_list, name=None):
"""Computes the global norm of multiple tensors.
Given a tuple or list of tensors `t_list`, this operation returns the
global norm of the elements in all tensors in `t_list`. The global norm is
computed as:
`global_norm = sqrt(sum([l2norm(t)**2 for t in t_list]))`
Any entries in `t_list` that are of type None are ignored.
Args:
t_list: A tuple or list of mixed `Tensors`, `IndexedSlices`, or None.
name: A name for the operation (optional).
Returns:
A 0-D (scalar) `Tensor` of type `float`.
Raises:
TypeError: If `t_list` is not a sequence.
"""
if (not isinstance(t_list, collections.Sequence)
or isinstance(t_list, six.string_types)):
raise TypeError("t_list should be a sequence")
t_list = list(t_list)
with ops.name_scope(name, "global_norm", t_list) as name:
values = [
ops.convert_to_tensor(
t.values if isinstance(t, ops.IndexedSlices) else t,
name="t_%d" % i)
if t is not None else t
for i, t in enumerate(t_list)]
half_squared_norms = []
for v in values:
if v is not None:
with ops.colocate_with(v):
half_squared_norms.append(gen_nn_ops.l2_loss(v))
half_squared_norm = math_ops.reduce_sum(array_ops.stack(half_squared_norms))
norm = math_ops.sqrt(
half_squared_norm *
constant_op.constant(2.0, dtype=half_squared_norm.dtype),
name="global_norm")
return norm
