class tf.contrib.bayesflow.variational_inference.ELBOForms Constants to control the elbo calculation. analytic_kl uses the analytic KL divergence between the variational distribution(s) and the prior(s). analytic_entropy uses the analytic entropy of the variational distribution(s). sample uses the sample KL or the sample entropy is the joint is provided. See elbo for what is used with default.

tf.contrib.distributions.Binomial.sample(sample_shape=(), seed=None, name='sample') Generate samples of the specified shape. Note that a call to sample() without arguments will generate a single sample. Args: sample_shape: 0D or 1D int32 Tensor. Shape of the generated samples. seed: Python integer seed for RNG name: name to give to the op. Returns: samples: a Tensor with prepended dimensions sample_shape.

int tensorflow::Tensor::dims() const Convenience accessor for the tensor shape. For all shape accessors, see comments for relevant methods of TensorShape in tensor_shape.h.

tf.contrib.learn.monitors.BaseMonitor.step_begin(step) Callback before training step begins. You may use this callback to request evaluation of additional tensors in the graph. Args: step: int, the current value of the global step. Returns: List of Tensor objects or string tensor names to be run. Raises: ValueError: if we've already begun a step, or step < 0, or step > max_steps.

class tf.contrib.bayesflow.stochastic_tensor.LaplaceWithSoftplusScaleTensor LaplaceWithSoftplusScaleTensor is a StochasticTensor backed by the distribution LaplaceWithSoftplusScale.

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

tf.contrib.learn.monitors.StepCounter.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.

tf.contrib.learn.train(graph, output_dir, train_op, loss_op, global_step_tensor=None, init_op=None, init_feed_dict=None, init_fn=None, log_every_steps=10, supervisor_is_chief=True, supervisor_master='', supervisor_save_model_secs=600, keep_checkpoint_max=5, supervisor_save_summaries_steps=100, feed_fn=None, steps=None, fail_on_nan_loss=True, monitors=None, max_steps=None) Train a model. Given graph, a directory to write outputs to (output_dir), and some ops, run a training loop. The given trai

tf.contrib.bayesflow.stochastic_tensor.BinomialTensor.input_dict

tf.contrib.distributions.LaplaceWithSoftplusScale.sample_n(n, seed=None, name='sample_n') Generate n samples. Args: n: Scalar Tensor of type int32 or int64, the number of observations to sample. seed: Python integer seed for RNG name: name to give to the op. Returns: samples: a Tensor with a prepended dimension (n,). Raises: TypeError: if n is not an integer type.