tfm.nlp.networks.Classification

Classification network head for BERT modeling.

tfm.nlp.networks.Classification(
    input_width,
    num_classes,
    initializer='glorot_uniform',
    output='logits',
    **kwargs
)

This network implements a simple classifier head based on a dense layer. If num_classes is one, it can be considered as a regression problem.

Args
`input_width`	The innermost dimension of the input tensor to this network.
`num_classes`	The number of classes that this network should classify to. If equal to 1, a regression problem is assumed.
`activation`	The activation, if any, for the dense layer in this network.
`initializer`	The initializer for the dense layer in this network. Defaults to a Glorot uniform initializer.
`output`	The output style for this network. Can be either `logits` or `predictions`.

Methods

call(
    inputs, training=None, mask=None
)

Calls the model on new inputs and returns the outputs as tensors.

In this case call() just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

Args
`inputs`	Input tensor, or dict/list/tuple of input tensors.
`training`	Boolean or boolean scalar tensor, indicating whether to run the `Network` in training mode or inference mode.
`mask`	A mask or list of masks. A mask can be either a boolean tensor or None (no mask). For more details, check the guide here.

Returns
A tensor if there is a single output, or a list of tensors if there are more than one outputs.