deepke.name_entity_re.standard.models.InferBert module

class deepke.name_entity_re.standard.models.InferBert.BertNer(config)[source]

Bases: pytorch_transformers.modeling_bert.BertForTokenClassification

forward(input_ids, token_type_ids=None, attention_mask=None, valid_ids=None)[source]

Defines the computation performed at every call.

Should be overridden by all subclasses.


Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool
class deepke.name_entity_re.standard.models.InferBert.InferNer(model_dir: str)[source]

Bases: object

load_model(model_dir: str, model_config: str = 'model_config.json')[source]
tokenize(text: str)[source]

tokenize input

preprocess(text: str)[source]
predict(text: str)[source]