BaseDecoder contructor.
The LayerVars for each layer of the decoder LSTM.
The LayerVars for projecting from the latent
variable z to the initial states of the LSTM layers.
The LayerVars for projecting from the output
of the LSTM to the logits of the output categorical distrubtion
(if nade is null) or to bias values to use in the NADE (if nade is
not null).
(optional) A Nade to use for computing the output vectors at
each step. If not given, the final projection values are used as logits
for a categorical distribution.
Decodes a batch of latent vectors, z.
If nade is parameterized, samples are generated using the MAP (argmax) of
the Bernoulli random variables from the NADE, and these bit vector makes up
the final dimension of the output.
If nade is not parameterized, sample labels are generated using the
MAP (argmax) of the logits output by the LSTM, and the onehots of those
labels makes up the final dimension of the output.
A batch of latent vectors to decode, sized [batchSize, zDims].
The length of decoded sequences.
(Optional) The softmax temperature to use when sampling from the logits. Argmax is used if not provided.
(Optional) Control tensors to use for conditioning, sized
[length, controlDepth].
A boolean tensor containing the decoded sequences, shaped
[batchSize, length, depth].
Generated using TypeDoc
LSTM decoder with optional NADE output.