deepr.layers.Select

class deepr.layers.Select(inputs=None, outputs=None, indices=None, n_in=None)

Layer to extract inputs / outputs from previous layers

The Select layer is particularly useful when defining arbitrary DAGs of layers : it is a convenient way to select which nodes should be inputs, and which should be outputs. For example:

layer = deepr.layers.Select(inputs=("x", "y"), outputs="z", n_in=2, indices=1)
layer((1, 2))  # 2
layer({"x": 1, "y": 2})  # {"z": 2}

See DAG documentation for more precisions.

__init__(inputs=None, outputs=None, indices=None, n_in=None)

Methods

__init__([inputs, outputs, indices, n_in])
forward(tensors[, mode])	Forward method of the layer
forward_as_dict(tensors[, mode])	Forward method on a dictionary of Tensors.