class tf.contrib.distributions.Uniform Uniform distribution with a and b parameters.

tf.contrib.distributions.LaplaceWithSoftplusScale.prob(value, name='prob') Probability density/mass function (depending on

tf.contrib.distributions.Multinomial.log_survival_function(value, name='log_survival_function') Log survival function.

tf.contrib.distributions.Dirichlet.log_prob(value, name='log_prob') Log probability density/mass function (depending on

tf.contrib.distributions.MultivariateNormalDiagWithSoftplusStDev.param_static_shapes(cls, sample_shape) param_shapes with static

tf.contrib.layers.separable_convolution2d(*args, **kwargs) Adds a depth-separable 2D convolution with optional batch_norm layer

tf.contrib.learn.TensorFlowRNNRegressor.fit(x, y, steps=None, monitors=None, logdir=None) Neural network model from provided

tf.contrib.learn.TensorFlowRNNRegressor.save(path) Saves checkpoints and graph to given path. Args:

class tf.contrib.learn.monitors.EveryN Base class for monitors that execute callbacks every N steps. This

tf.nn.rnn_cell.BasicLSTMCell.zero_state(batch_size, dtype) Return zero-filled state tensor(s). Args: