aeppl.scan.MeasurableScan#

class aeppl.scan.MeasurableScan(inputs, outputs, info, mode=None, typeConstructor=None, truncate_gradient=-1, name=None, as_while=False, profile=None, allow_gc=True, strict=True)[source]#

A placeholder used to specify a log-likelihood for a scan sub-graph.

Parameters

Methods

MeasurableScan.L_op(inputs, outs, dC_douts)

Construct a graph for the L-operator.

MeasurableScan.R_op(inputs, eval_points)

Construct a graph for the R-operator.

MeasurableScan.__init__(inputs, outputs, info)

type inputs

List[Variable]

MeasurableScan.add_tag_trace([user_line])

Add tag.trace to a node or variable.

MeasurableScan.clone()

Clone the Op and its inner-graph.

MeasurableScan.connection_pattern(node)

MeasurableScan.do_constant_folding(fgraph, node)

Determine whether or not constant folding should be performed for the given node.

MeasurableScan.get_oinp_iinp_iout_oout_mappings()

Compute and return dictionary mappings between the inputs and outputs of the inner function and the inputs and outputs of the Scan node in the outer graph.

MeasurableScan.get_params(node)

Try to get parameters for the Op when Op.params_type is set to a ParamsType.

MeasurableScan.grad(inputs, output_grads)

Construct a graph for the gradient with respect to each input variable.

MeasurableScan.infer_shape(fgraph, node, ...)

MeasurableScan.inner_mitmot(list_inputs)

MeasurableScan.inner_mitmot_outs(list_outputs)

MeasurableScan.inner_mitsot(list_inputs)

MeasurableScan.inner_mitsot_outs(list_outputs)

MeasurableScan.inner_nitsot_outs(list_outputs)

MeasurableScan.inner_non_seqs(list_inputs)

MeasurableScan.inner_seqs(list_inputs)

MeasurableScan.inner_shared(list_inputs)

MeasurableScan.inner_shared_outs(list_outputs)

MeasurableScan.inner_sitsot(list_inputs)

MeasurableScan.inner_sitsot_outs(list_outputs)

MeasurableScan.make_node(*inputs)

The inputs to this method take the following form:

MeasurableScan.make_py_thunk(node, ...[, debug])

Make a Python thunk.

MeasurableScan.make_thunk(node, storage_map, ...)

param node

Something previously returned by self.make_node.

MeasurableScan.outer_mitmot(list_inputs)

MeasurableScan.outer_mitmot_outs(list_outputs)

MeasurableScan.outer_mitsot(list_inputs)

MeasurableScan.outer_mitsot_outs(list_outputs)

MeasurableScan.outer_nitsot(list_inputs)

MeasurableScan.outer_nitsot_outs(list_outputs)

MeasurableScan.outer_non_seqs(list_inputs)

MeasurableScan.outer_seqs(list_inputs)

MeasurableScan.outer_shared(list_inputs)

MeasurableScan.outer_shared_outs(list_outputs)

MeasurableScan.outer_sitsot(list_inputs)

MeasurableScan.outer_sitsot_outs(list_outputs)

MeasurableScan.perform(node, inputs, ...[, ...])

Compute the scan operation in Python.

MeasurableScan.prepare_fgraph(fgraph)

Update and wrap fgraph's inputs and outputs in preparation for compilation.

MeasurableScan.prepare_node(node, ...)

Make any special modifications that the Op needs before doing Op.make_thunk.

MeasurableScan.validate_inner_graph()

Perform some elementary validations on the inner graph to ensure that it is coherent.

Attributes

default_output

An int that specifies which output Op.__call__ should return.

destroy_map

A dict that maps output indices to the input indices upon which they operate in-place.

fn

Lazily compile the inner function graph.

inner_inputs

The inner function's inputs.

inner_outputs

The inner function's outputs.

itypes

otypes

params_type

view_map

A dict that maps output indices to the input indices of which they are a view.