tf.contrib.opt.ExternalOptimizerInterface

View source on GitHub

Base class for interfaces with external optimization algorithms.

tf.contrib.opt.ExternalOptimizerInterface(
    loss, var_list=None, equalities=None, inequalities=None, var_to_bounds=None,
    **optimizer_kwargs
)

Subclass this and implement _minimize in order to wrap a new optimization algorithm.

ExternalOptimizerInterface should not be instantiated directly; instead use e.g. ScipyOptimizerInterface.

loss A scalar Tensor to be minimized.
var_list Optional list of Variable objects to update to minimize loss. Defaults to the list of variables collected in the graph under the key GraphKeys.TRAINABLE_VARIABLES.
equalities Optional list of equality constraint scalar Tensors to be held equal to zero.
inequalities Optional list of inequality constraint scalar Tensors to be held nonnegative.
var_to_bounds Optional dict where each key is an optimization Variable and each corresponding value is a length-2 tuple of (low, high) bounds. Although enforcing this kind of simple constraint could be accomplished with the inequalities arg, not all optimization algorithms support general inequality constraints, e.g. L-BFGS-B. Both low and high can either be numbers or anything convertible to a NumPy array that can be broadcast to the shape of var (using np.broadcast_to). To indicate that there is no bound, use None (or +/- np.infty). For example, if var is a 2x3 matrix, then any of the following corresponding bounds could be supplied:

  • (0, np.infty): Each element of var held positive.
  • (-np.infty, [1, 2]): First column less than 1, second column less than 2.
  • (-np.infty, [[1], [2], [3]]): First row less than 1, second row less than 2, etc.
  • (-np.infty, [[1, 2, 3], [4, 5, 6]]): Entry var[0, 0] less than 1, var[0, 1] less than 2, etc.
**optimizer_kwargs Other subclass-specific keyword arguments.

Methods

minimize

View source

minimize(
    session=None, feed_dict=None, fetches=None, step_callback=None,
    loss_callback=None, **run_kwargs
)

Minimize a scalar Tensor.

Variables subject to optimization are updated in-place at the end of optimization.

Note that this method does not just return a minimization Op, unlike Optimizer.minimize(); instead it actually performs minimization by executing commands to control a Session.

Args
session A Session instance.
feed_dict A feed dict to be passed to calls to session.run.
fetches A list of Tensors to fetch and supply to loss_callback as positional arguments.
step_callback A function to be called at each optimization step; arguments are the current values of all optimization variables flattened into a single vector.
loss_callback A function to be called every time the loss and gradients are computed, with evaluated fetches supplied as positional arguments.
**run_kwargs kwargs to pass to session.run.