![]() |
A autoregressively masked dense layer. (deprecated)
tf.contrib.distributions.bijectors.masked_dense(
inputs,
units,
num_blocks=None,
exclusive=False,
kernel_initializer=None,
reuse=None,
name=None,
*args,
**kwargs
)
Analogous to tf.compat.v1.layers.dense
.
See [Germain et al. (2015)][1] for detailed explanation.
Arguments:
inputs
: Tensor input.units
: Pythonint
scalar representing the dimensionality of the output space.num_blocks
: Pythonint
scalar representing the number of blocks for the MADE masks.exclusive
: Pythonbool
scalar representing whether to zero the diagonal of the mask, used for the first layer of a MADE.kernel_initializer
: Initializer function for the weight matrix. IfNone
(default), weights are initialized using thetf.glorot_random_initializer
.reuse
: Pythonbool
scalar representing whether to reuse the weights of a previous layer by the same name.name
: Pythonstr
used to describe ops managed by this function.*args
:tf.compat.v1.layers.dense
arguments.**kwargs
:tf.compat.v1.layers.dense
keyword arguments.
Returns:
Output tensor.
Raises:
NotImplementedError
: if rightmost dimension ofinputs
is unknown prior to graph execution.
References
[1]: Mathieu Germain, Karol Gregor, Iain Murray, and Hugo Larochelle. MADE: Masked Autoencoder for Distribution Estimation. In International Conference on Machine Learning, 2015. https://arxiv.org/abs/1502.03509