TextClassifier

class flash.text.classification.model.TextClassifier(num_classes=None, labels=None, backbone='prajjwal1/bert-medium', max_length=128, loss_fn=None, optimizer='Adam', lr_scheduler=None, metrics=None, learning_rate=None, multi_label=False, enable_ort=False, **kwargs)

The TextClassifier is a Task for classifying text. For more details, see Text Classification. The TextClassifier also supports multi-label classification with multi_label=True. For more details, see Multi-label Text Classification.

Parameters

• num_classes (Optional[int]) – Number of classes to classify.

• backbone (str) – A model to use to compute text features can be any BERT model from HuggingFace/transformersimage.

• max_length (int) – The maximum length to pad / truncate sequences to.

• optimizer (TypeVar(OPTIMIZER_TYPE, str, Callable, Tuple[str, Dict[str, Any]], None)) – Optimizer to use for training.

• lr_scheduler (Optional[TypeVar(LR_SCHEDULER_TYPE, str, Callable, Tuple[str, Dict[str, Any]], Tuple[str, Dict[str, Any], Dict[str, Any]], None)]) – The LR scheduler to use during training.

• metrics (Optional[TypeVar(METRICS_TYPE, Metric, Mapping, Sequence, None)]) – Metrics to compute for training and evaluation. Can either be an metric from the torchmetrics package, a custom metric inherenting from torchmetrics.Metric, a callable function or a list/dict containing a combination of the aforementioned. In all cases, each metric needs to have the signature metric(preds,target) and return a single scalar tensor. Defaults to torchmetrics.Accuracy.

• learning_rate (Optional[float]) – Learning rate to use for training, defaults to 1e-3

• multi_label (bool) – Whether the targets are multi-label or not.

• enable_ort (bool) – Enable Torch ONNX Runtime Optimization: https://onnxruntime.ai/docs/#onnx-runtime-for-training

classmethod available_finetuning_strategies(cls)

Returns a list containing the keys of the available Finetuning Strategies.

Return type

List[str]

classmethod available_lr_schedulers(cls)

Returns a list containing the keys of the available LR schedulers.

Return type

List[str]

classmethod available_optimizers(cls)

Returns a list containing the keys of the available Optimizers.

Return type

List[str]

classmethod available_outputs(cls)

Returns the list of available outputs (that can be used during prediction or serving) for this Task.

Examples

..testsetup:

>>> from flash import Task

>>> print(Task.available_outputs())
['preds', 'raw']

Return type

List[str]