Model¶

class baikal.Model(inputs, outputs, targets=None, name=None)¶

Bases: baikal._core.step.Step

A Model is a network (more precisely, a directed acyclic graph) of Steps, and it is defined from the input/output specification of the pipeline. Models have fit and predict routines that, together with graph-based engine, allow the automatic (feed-forward) computation of each of the pipeline steps when fed with data.

Parameters

inputs – Inputs to the model.
outputs – Outputs of the model.
targets – Targets of the model.
name – Name of the model (optional). If no name is passed, a name will be automatically generated.

Methods

`fit`(X[, y])	Trains the model on the given input and target data.
`get_compute_func_at`(port)	Get compute function at the specified port.
`get_data_placeholder`(name)	Get a data placeholder (graph half-edge) in the model by name.
`get_fit_compute_func_at`(port)	Get fit-compute function at the specified port.
`get_inputs_at`(port)	Get inputs at the specified port.
`get_outputs_at`(port)	Get outputs at the specified port.
`get_params`([deep])	Get the parameters of the model.
`get_step`(name)	Get a step (graph node) in the model by name.
`get_targets_at`(port)	Get targets at the specified port.
`get_trainable_at`(port)	Get trainable flag at the specified port.
`predict`(X[, output_names])	Predict by applying the model on the given input data.
`set_compute_func_at`(port, value)	Set compute function at the specified port.
`set_fit_compute_func_at`(port, value)	Set fit-compute function at the specified port.
`set_params`(**params)	Set the parameters of the model.
`set_trainable_at`(port, value)	Set trainable flag at the specified port.
`__call__`(inputs[, targets, compute_func, …])	Call the step on input(s) (from previous steps) and generates the output(s) to be used in further steps.

Attributes

`compute_func`	Get the compute function of the step.
`fit_compute_func`	Get the fit-compute function of the step.
`graph`	Get the graph associated to the model.
`inputs`	Get the inputs of the step.
`n_outputs`	Get the number of outputs the step produces.
`name`	Get the name of the step.
`outputs`	Get the outputs of the step.
`targets`	Get the targets of the step.
`trainable`	Get trainable flag of the step.