TrainablePipe

This class is a base class and not instantiated directly. Trainable pipeline components like the EntityRecognizer or TextCategorizer inherit from it and it defines the interface that components should follow to function as trainable components in a spaCy pipeline. See the docs on writing trainable components for how to use the TrainablePipe base class to implement custom components.

Why is it implemented in Cython?

The TrainablePipe class is implemented in a .pyx module, the extension used by Cython. This is needed so that other Cython classes, like the EntityRecognizer can inherit from it. But it doesn't mean you have to implement trainable components in Cython – pure Python components like the TextCategorizer can also inherit from TrainablePipe.

%%GITHUB_SPACY/spacy/pipeline/trainable_pipe.pyx

TrainablePipe.__init__ {id="init",tag="method"}

Example

pythonCopy

from spacy.pipeline import TrainablePipe
from spacy.language import Language

class CustomPipe(TrainablePipe):
    ...

@Language.factory("your_custom_pipe", default_config={"model": MODEL})
def make_custom_pipe(nlp, name, model):
    return CustomPipe(nlp.vocab, model, name)

Create a new pipeline instance. In your application, you would normally use a shortcut for this and instantiate the component using its string name and nlp.add_pipe.

TrainablePipe.__call__ {id="call",tag="method"}

Apply the pipe to one document. The document is modified in place, and returned. This usually happens under the hood when the nlp object is called on a text and all pipeline components are applied to the Doc in order. Both __call__ and pipe delegate to the predict and set_annotations methods.

Example

pythonCopy

doc = nlp("This is a sentence.")
pipe = nlp.add_pipe("your_custom_pipe")
# This usually happens under the hood
processed = pipe(doc)

TrainablePipe.pipe {id="pipe",tag="method"}

Apply the pipe to a stream of documents. This usually happens under the hood when the nlp object is called on a text and all pipeline components are applied to the Doc in order. Both __call__ and pipe delegate to the predict and set_annotations methods.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
for doc in pipe.pipe(docs, batch_size=50):
    pass

TrainablePipe.set_error_handler {id="set_error_handler",tag="method",version="3"}

Define a callback that will be invoked when an error is thrown during processing of one or more documents with either __call__ or pipe. The error handler will be invoked with the original component's name, the component itself, the list of documents that was being processed, and the original error.

Example

pythonCopy

def warn_error(proc_name, proc, docs, e):
    print(f"An error occurred when applying component {proc_name}.")

pipe = nlp.add_pipe("ner")
pipe.set_error_handler(warn_error)

TrainablePipe.get_error_handler {id="get_error_handler",tag="method",version="3"}

Retrieve the callback that performs error handling for this component's __call__ and pipe methods. If no custom function was previously defined with set_error_handler, a default function is returned that simply reraises the exception.

Example

pythonCopy

pipe = nlp.add_pipe("ner")
error_handler = pipe.get_error_handler()

TrainablePipe.initialize {id="initialize",tag="method",version="3"}

Initialize the component for training. get_examples should be a function that returns an iterable of Example objects. The data examples are used to initialize the model of the component and can either be the full training data or a representative sample. Initialization includes validating the network, inferring missing shapes and setting up the label scheme based on the data. This method is typically called by Language.initialize.

This method was previously called begin_training.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
pipe.initialize(lambda: [], pipeline=nlp.pipeline)

TrainablePipe.predict {id="predict",tag="method"}

Apply the component's model to a batch of Doc objects, without modifying them.

This method needs to be overwritten with your own custom predict method.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
scores = pipe.predict([doc1, doc2])

TrainablePipe.set_annotations {id="set_annotations",tag="method"}

Modify a batch of Doc objects, using pre-computed scores.

This method needs to be overwritten with your own custom set_annotations method.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
scores = pipe.predict(docs)
pipe.set_annotations(docs, scores)

TrainablePipe.update {id="update",tag="method"}

Learn from a batch of Example objects containing the predictions and gold-standard annotations, and update the component's model.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
optimizer = nlp.initialize()
losses = pipe.update(examples, sgd=optimizer)

TrainablePipe.rehearse {id="rehearse",tag="method,experimental",version="3"}

Perform a "rehearsal" update from a batch of data. Rehearsal updates teach the current model to make predictions similar to an initial model, to try to address the "catastrophic forgetting" problem. This feature is experimental.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
optimizer = nlp.resume_training()
losses = pipe.rehearse(examples, sgd=optimizer)

TrainablePipe.get_loss {id="get_loss",tag="method"}

Find the loss and gradient of loss for the batch of documents and their predicted scores.

This method needs to be overwritten with your own custom get_loss method.

Example

pythonCopy

ner = nlp.add_pipe("ner")
scores = ner.predict([eg.predicted for eg in examples])
loss, d_loss = ner.get_loss(examples, scores)

TrainablePipe.score {id="score",tag="method",version="3"}

Score a batch of examples.

Example

pythonCopy

scores = pipe.score(examples)

TrainablePipe.create_optimizer {id="create_optimizer",tag="method"}

Create an optimizer for the pipeline component. Defaults to Adam with default settings.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
optimizer = pipe.create_optimizer()

TrainablePipe.use_params {id="use_params",tag="method, contextmanager"}

Modify the pipe's model, to use the given parameter values. At the end of the context, the original parameters are restored.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
with pipe.use_params(optimizer.averages):
    pipe.to_disk("/best_model")

TrainablePipe.finish_update {id="finish_update",tag="method"}

Update parameters using the current parameter gradients. Defaults to calling self.model.finish_update.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
optimizer = nlp.initialize()
losses = pipe.update(examples, sgd=None)
pipe.finish_update(sgd)

TrainablePipe.add_label {id="add_label",tag="method"}

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
pipe.add_label("MY_LABEL")

Add a new label to the pipe, to be predicted by the model. The actual implementation depends on the specific component, but in general add_label shouldn't be called if the output dimension is already set, or if the model has already been fully initialized. If these conditions are violated, the function will raise an Error. The exception to this rule is when the component is resizable, in which case set_output should be called to ensure that the model is properly resized.

This method needs to be overwritten with your own custom add_label method.

Note that in general, you don't have to call pipe.add_label if you provide a representative data sample to the initialize method. In this case, all labels found in the sample will be automatically added to the model, and the output dimension will be inferred automatically.

TrainablePipe.is_resizable {id="is_resizable",tag="property"}

Example

pythonCopy

can_resize = pipe.is_resizable

With custom resizing implemented by a component:

pythonCopy

def custom_resize(model, new_nO):
    # adjust model
    return model

custom_model.attrs["resize_output"] = custom_resize

Check whether or not the output dimension of the component's model can be resized. If this method returns True, set_output can be called to change the model's output dimension.

For built-in components that are not resizable, you have to create and train a new model from scratch with the appropriate architecture and output dimension. For custom components, you can implement a resize_output function and add it as an attribute to the component's model.

TrainablePipe.set_output {id="set_output",tag="method"}

Change the output dimension of the component's model. If the component is not resizable, this method will raise a NotImplementedError. If a component is resizable, the model's attribute resize_output will be called. This is a function that takes the original model and the new output dimension nO, and changes the model in place. When resizing an already trained model, care should be taken to avoid the "catastrophic forgetting" problem.

Example

pythonCopy

if pipe.is_resizable:
    pipe.set_output(512)

TrainablePipe.to_disk {id="to_disk",tag="method"}

Serialize the pipe to disk.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
pipe.to_disk("/path/to/pipe")

TrainablePipe.from_disk {id="from_disk",tag="method"}

Load the pipe from disk. Modifies the object in place and returns it.

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
pipe.from_disk("/path/to/pipe")

TrainablePipe.to_bytes {id="to_bytes",tag="method"}

Example

pythonCopy

pipe = nlp.add_pipe("your_custom_pipe")
pipe_bytes = pipe.to_bytes()

Serialize the pipe to a bytestring.

TrainablePipe.from_bytes {id="from_bytes",tag="method"}

Load the pipe from a bytestring. Modifies the object in place and returns it.

Example

pythonCopy

pipe_bytes = pipe.to_bytes()
pipe = nlp.add_pipe("your_custom_pipe")
pipe.from_bytes(pipe_bytes)

Attributes {id="attributes"}

Serialization fields {id="serialization-fields"}

During serialization, spaCy will export several data fields used to restore different aspects of the object. If needed, you can exclude them from serialization by passing in the string names via the exclude argument.

Example

pythonCopy

data = pipe.to_disk("/path")