tf.zeros_like(tensor, dtype=None, name=None, optimize=True) Creates a tensor with all elements set to zero.

tf.ones_like(tensor, dtype=None, name=None, optimize=True) Creates a tensor with all elements set to 1. Given

tf.random_uniform(shape, minval=0, maxval=None, dtype=tf.float32, seed=None, name=None) Outputs random values from a uniform distribution

tf.truncated_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None) Outputs random values from a truncated

tf.set_random_seed(seed) Sets the graph-level random seed. Operations that rely on a random seed

tf.multinomial(logits, num_samples, seed=None, name=None) Draws samples from a multinomial distribution.

tf.random_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None) Outputs random values from a normal distribution

tf.random_crop(value, size, seed=None, name=None) Randomly crops a tensor to a given size. Slices

tf.constant(value, dtype=None, shape=None, name='Const') Creates a constant tensor. The resulting

tf.random_gamma(shape, alpha, beta=None, dtype=tf.float32, seed=None, name=None) Draws shape samples from each of