tfm.nlp.models.XLNetClassifier

Classifier model based on XLNet.

tfm.nlp.models.XLNetClassifier(
    network: Union[tf.keras.layers.Layer, tf.keras.Model],
    num_classes: int,
    initializer: tf.keras.initializers.Initializer = 'random_normal',
    summary_type: str = 'last',
    dropout_rate: float = 0.1,
    head_name: str = 'sentence_prediction',
    **kwargs
)

This is an implementation of the network structure surrounding a Transformer-XL encoder as described in "XLNet: Generalized Autoregressive Pretraining for Language Understanding" (https://arxiv.org/abs/1906.08237).

Note: This model does not use utilize the memory mechanism used in the original XLNet Classifier.

Args
network	An XLNet/Transformer-XL based network. This network should output a sequence output and list of state tensors.
num_classes	Number of classes to predict from the classification network.
initializer	The initializer (if any) to use in the classification networks. Defaults to a RandomNormal initializer.
summary_type	Method used to summarize a sequence into a compact vector.
dropout_rate	The dropout probability of the cls head.
head_name	Name of the classification head.

Attributes
checkpoint_items

Methods

call

View source

call(
    inputs: Mapping[str, Any]
)

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).

Note: This method should not be called directly. It is only meant to be overridden when subclassing tf.keras.Model. To call a model on an input, always use the __call__() method, i.e. model(inputs), which relies on the underlying call() method.

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.