def TextCatCNN_v1(tok2vec: Model, exclusive_classes: bool, nO: Optional[int] = None) -> Model[List[Doc], Floats2d]: """ Build a simple CNN text classifier, given a token-to-vector model as inputs. If exclusive_classes=True, a softmax non-linearity is applied, so that the outputs sum to 1. If exclusive_classes=False, a logistic non-linearity is applied instead, so that outputs are in the range [0, 1]. """ chain = registry.get("layers", "chain.v1") reduce_mean = registry.get("layers", "reduce_mean.v1") Logistic = registry.get("layers", "Logistic.v1") Softmax = registry.get("layers", "Softmax.v1") Linear = registry.get("layers", "Linear.v1") list2ragged = registry.get("layers", "list2ragged.v1") with Model.define_operators({">>": chain}): cnn = tok2vec >> list2ragged() >> reduce_mean() if exclusive_classes: output_layer = Softmax(nO=nO, nI=tok2vec.maybe_get_dim("nO")) model = cnn >> output_layer model.set_ref("output_layer", output_layer) else: linear_layer = Linear(nO=nO, nI=tok2vec.maybe_get_dim("nO")) model = cnn >> linear_layer >> Logistic() model.set_ref("output_layer", linear_layer) model.set_ref("tok2vec", tok2vec) model.set_dim("nO", nO) model.attrs["multi_label"] = not exclusive_classes return model
def build_nel_encoder(tok2vec: Model, nO: Optional[int] = None) -> Model: with Model.define_operators({">>": chain, "**": clone}): token_width = tok2vec.maybe_get_dim("nO") output_layer = Linear(nO=nO, nI=token_width) model = (tok2vec >> list2ragged() >> reduce_mean() >> residual( Maxout(nO=token_width, nI=token_width, nP=2, dropout=0.0)) >> output_layer) model.set_ref("output_layer", output_layer) model.set_ref("tok2vec", tok2vec) return model
def build_nel_encoder(tok2vec: Model, nO: Optional[int] = None) -> Model[List[Doc], Floats2d]: with Model.define_operators({">>": chain, "&": tuplify}): token_width = tok2vec.maybe_get_dim("nO") output_layer = Linear(nO=nO, nI=token_width) model = (((tok2vec >> list2ragged()) & build_span_maker()) >> extract_spans() >> reduce_mean() >> residual( Maxout(nO=token_width, nI=token_width, nP=2, dropout=0.0)) >> output_layer) model.set_ref("output_layer", output_layer) model.set_ref("tok2vec", tok2vec) # flag to show this isn't legacy model.attrs["include_span_maker"] = True return model
def build_simple_cnn_text_classifier( tok2vec: Model, exclusive_classes: bool, nO: Optional[int] = None) -> Model[List[Doc], Floats2d]: """ Build a simple CNN text classifier, given a token-to-vector model as inputs. If exclusive_classes=True, a softmax non-linearity is applied, so that the outputs sum to 1. If exclusive_classes=False, a logistic non-linearity is applied instead, so that outputs are in the range [0, 1]. """ fill_defaults = {"b": 0, "W": 0} with Model.define_operators({">>": chain}): cnn = tok2vec >> list2ragged() >> reduce_mean() nI = tok2vec.maybe_get_dim("nO") if exclusive_classes: output_layer = Softmax(nO=nO, nI=nI) fill_defaults["b"] = NEG_VALUE resizable_layer: Model = resizable( output_layer, resize_layer=partial(resize_linear_weighted, fill_defaults=fill_defaults), ) model = cnn >> resizable_layer else: output_layer = Linear(nO=nO, nI=nI) resizable_layer = resizable( output_layer, resize_layer=partial(resize_linear_weighted, fill_defaults=fill_defaults), ) model = cnn >> resizable_layer >> Logistic() model.set_ref("output_layer", output_layer) model.attrs["resize_output"] = partial( resize_and_set_ref, resizable_layer=resizable_layer, ) model.set_ref("tok2vec", tok2vec) model.set_dim( "nO", nO ) # type: ignore # TODO: remove type ignore once Thinc has been updated model.attrs["multi_label"] = not exclusive_classes return model