tf.contrib.learn.monitors.EveryN.epoch_end()

tf.contrib.learn.monitors.EveryN.epoch_end(epoch) End epoch. Args: epoch: int, the epoch number. Raises: ValueError: if we've not begun an epoch, or epoch number does not match.

tensorflow::TensorShape::operator==()

bool tensorflow::TensorShape::operator==(const TensorShape &b) const

tf.contrib.distributions.Dirichlet.variance()

tf.contrib.distributions.Dirichlet.variance(name='variance') Variance.

tensorflow::Thread

Member Details tensorflow::Thread::Thread() tensorflow::Thread::~Thread() Blocks until the thread of control stops running.

tf.contrib.losses.hinge_loss()

tf.contrib.losses.hinge_loss(logits, target, scope=None) Method that returns the loss tensor for hinge loss. Args: logits: The logits, a float tensor. target: The ground truth output tensor. Its shape should match the shape of logits. The values of the tensor are expected to be 0.0 or 1.0. scope: The scope for the operations performed in computing the loss. Returns: A Tensor of same shape as logits and target representing the loss values across the batch. Raises: ValueError: If the shape

tf.nn.rnn_cell.EmbeddingWrapper.output_size

tf.nn.rnn_cell.EmbeddingWrapper.output_size

tf.contrib.bayesflow.stochastic_tensor.CategoricalTensor.name

tf.contrib.bayesflow.stochastic_tensor.CategoricalTensor.name

tf.contrib.graph_editor.SubGraphView.__str__()

tf.contrib.graph_editor.SubGraphView.__str__()

tf.contrib.distributions.QuantizedDistribution.mode()

tf.contrib.distributions.QuantizedDistribution.mode(name='mode') Mode.

tf.contrib.learn.monitors.StepCounter.end()

tf.contrib.learn.monitors.StepCounter.end(session=None)