tf.contrib.losses.get_total_loss(add_regularization_losses=True, name='total_loss') Returns a tensor whose value represents the total loss. Notice that the function adds the given losses to the regularization losses. Args: add_regularization_losses: A boolean indicating whether or not to use the regularization losses in the sum. name: The name of the returned tensor. Returns: A Tensor whose value represents the total loss. Raises: ValueError: if losses is not iterable.

tf.matrix_set_diag(input, diagonal, name=None) Returns a batched matrix tensor with new batched diagonal values. Given input and diagonal, this operation returns a tensor with the same shape and values as input, except for the diagonals of the innermost matrices. These will be overwritten by the values in diagonal. The batched matrices must be square. The output is computed as follows: Assume input has k+1 dimensions [I, J, K, ..., N, N] and diagonal has k dimensions [I, J, K, ..., N]. Then th

int64 tensorflow::TensorShape::dim_size(int d) const Returns the number of elements in dimension d. REQUIRES: 0 <= d < dims()

string tensorflow::TensorShapeUtils::ShapeListString(const gtl::ArraySlice< TensorShape > &shapes)

tf.SparseTensor.indices The indices of non-zero values in the represented dense tensor. Returns: A 2-D Tensor of int64 with shape [N, ndims], where N is the number of non-zero values in the tensor, and ndims is the rank.

tf.contrib.bayesflow.stochastic_tensor.InverseGammaTensor.mean(name='mean')

class tf.contrib.distributions.Distribution A generic probability distribution base class. Distribution is a base class for constructing and organizing properties (e.g., mean, variance) of random variables (e.g, Bernoulli, Gaussian).

tf.contrib.learn.LinearRegressor.config

static bool tensorflow::TensorShapeUtils::IsScalar(const TensorShape &shape)

tf.contrib.distributions.Gamma.mean(name='mean') Mean.