static Status tensorflow::PartialTensorShape::MakePartialShape(const int32 *dims, int n, PartialTensorShape *out) Returns a PartialTensorShape whose dimensions are dims[0], dims[1], ..., dims[n-1]. Values of -1 are considered "unknown".

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

tf.contrib.distributions.QuantizedDistribution.dtype The DType of Tensors handled by this Distribution.

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

tf.contrib.distributions.NormalWithSoftplusSigma.pmf(value, name='pmf') Probability mass function. Args: value: float or double Tensor. name: The name to give this op. Returns: pmf: a Tensor of shape sample_shape(x) + self.batch_shape with values of type self.dtype. Raises: TypeError: if is_continuous.

tf.nn.rnn_cell.BasicRNNCell.__call__(inputs, state, scope=None) Most basic RNN: output = new_state = activation(W * input + U * state + B).

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

tf.contrib.learn.LinearRegressor.config

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.distributions.BernoulliWithSigmoidP.entropy(name='entropy') Shanon entropy in nats.