mirror of
https://github.com/explosion/spaCy.git
synced 2025-04-20 00:51:58 +03:00
Merge remote-tracking branch 'upstream/master' into feature/textcat-paramteric-attention
This commit is contained in:
Daniël de Kok
commit
8a33169725
2
.github/FUNDING.yml
vendored
2
.github/FUNDING.yml
vendored
|
|
@ -1 +1 @@
|
|||
custom: https://explosion.ai/merch
|
||||
custom: [https://explosion.ai/merch, https://explosion.ai/tailored-solutions]
|
||||
|
|
|
|||
|
|
@ -39,26 +39,31 @@ open-source software, released under the
|
|||
| 🚀 **[New in v3.0]** | New features, backwards incompatibilities and migration guide. |
|
||||
| 🪐 **[Project Templates]** | End-to-end workflows you can clone, modify and run. |
|
||||
| 🎛 **[API Reference]** | The detailed reference for spaCy's API. |
|
||||
| ⏩ **[GPU Processing]** | Use spaCy with CUDA-compatible GPU processing. |
|
||||
| 📦 **[Models]** | Download trained pipelines for spaCy. |
|
||||
| 🦙 **[Large Language Models]** | Integrate LLMs into spaCy pipelines. |
|
||||
| 🌌 **[Universe]** | Plugins, extensions, demos and books from the spaCy ecosystem. |
|
||||
| ⚙️ **[spaCy VS Code Extension]** | Additional tooling and features for working with spaCy's config files. |
|
||||
| 👩🏫 **[Online Course]** | Learn spaCy in this free and interactive online course. |
|
||||
| 📰 **[Blog]** | Read about current spaCy and Prodigy development, releases, talks and more from Explosion. |
|
||||
| 📺 **[Videos]** | Our YouTube channel with video tutorials, talks and more. |
|
||||
| 🛠 **[Changelog]** | Changes and version history. |
|
||||
| 💝 **[Contribute]** | How to contribute to the spaCy project and code base. |
|
||||
| 👕 **[Swag]** | Support us and our work with unique, custom-designed swag! |
|
||||
| <a href="https://explosion.ai/spacy-tailored-pipelines"><img src="https://user-images.githubusercontent.com/13643239/152853098-1c761611-ccb0-4ec6-9066-b234552831fe.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Get a custom spaCy pipeline, tailor-made for your NLP problem by spaCy's core developers. Streamlined, production-ready, predictable and maintainable. Start by completing our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more →](https://explosion.ai/spacy-tailored-pipelines)** |
|
||||
| <a href="https://explosion.ai/spacy-tailored-analysis"><img src="https://user-images.githubusercontent.com/1019791/206151300-b00cd189-e503-4797-aa1e-1bb6344062c5.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Bespoke advice for problem solving, strategy and analysis for applied NLP projects. Services include data strategy, code reviews, pipeline design and annotation coaching. Curious? Fill in our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more →](https://explosion.ai/spacy-tailored-analysis)** |
|
||||
| <a href="https://explosion.ai/tailored-solutions"><img src="https://github.com/explosion/spaCy/assets/13643239/36d2a42e-98c0-4599-90e1-788ef75181be" width="150" alt="Tailored Solutions"/></a> | Custom NLP consulting, implementation and strategic advice by spaCy’s core development team. Streamlined, production-ready, predictable and maintainable. Send us an email or take our 5-minute questionnaire, and well'be in touch! **[Learn more →](https://explosion.ai/tailored-solutions)** |
|
||||
|
||||
[spacy 101]: https://spacy.io/usage/spacy-101
|
||||
[new in v3.0]: https://spacy.io/usage/v3
|
||||
[usage guides]: https://spacy.io/usage/
|
||||
[api reference]: https://spacy.io/api/
|
||||
[gpu processing]: https://spacy.io/usage#gpu
|
||||
[models]: https://spacy.io/models
|
||||
[large language models]: https://spacy.io/usage/large-language-models
|
||||
[universe]: https://spacy.io/universe
|
||||
[spacy vs code extension]: https://github.com/explosion/spacy-vscode
|
||||
[videos]: https://www.youtube.com/c/ExplosionAI
|
||||
[online course]: https://course.spacy.io
|
||||
[blog]: https://explosion.ai
|
||||
[project templates]: https://github.com/explosion/projects
|
||||
[changelog]: https://spacy.io/usage#changelog
|
||||
[contribute]: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md
|
||||
|
|
|
|||
|
|
@ -984,6 +984,9 @@ class Errors(metaclass=ErrorsWithCodes):
|
|||
E1055 = ("The 'replace_listener' callback expects {num_params} parameters, "
|
||||
"but only callbacks with one or three parameters are supported")
|
||||
E1056 = ("The `TextCatBOW` architecture expects a length of at least 1, was {length}.")
|
||||
E1057 = ("The `TextCatReduce` architecture must be used with at least one "
|
||||
"reduction. Please enable one of `use_reduce_first`, "
|
||||
"`use_reduce_last`, `use_reduce_max` or `use_reduce_mean`.")
|
||||
|
||||
|
||||
# Deprecated model shortcuts, only used in errors and warnings
|
||||
|
|
|
|||
|
|
@ -19,6 +19,9 @@ from thinc.api import (
|
|||
clone,
|
||||
concatenate,
|
||||
list2ragged,
|
||||
reduce_first,
|
||||
reduce_last,
|
||||
reduce_max,
|
||||
reduce_mean,
|
||||
reduce_sum,
|
||||
residual,
|
||||
|
|
@ -51,39 +54,15 @@ def build_simple_cnn_text_classifier(
|
|||
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)
|
||||
if nO is not None:
|
||||
model.set_dim("nO", cast(int, nO))
|
||||
model.attrs["multi_label"] = not exclusive_classes
|
||||
return model
|
||||
return build_reduce_text_classifier(
|
||||
tok2vec=tok2vec,
|
||||
exclusive_classes=exclusive_classes,
|
||||
use_reduce_first=False,
|
||||
use_reduce_last=False,
|
||||
use_reduce_max=False,
|
||||
use_reduce_mean=True,
|
||||
nO=nO,
|
||||
)
|
||||
|
||||
|
||||
def resize_and_set_ref(model, new_nO, resizable_layer):
|
||||
|
|
@ -299,4 +278,80 @@ def _init_parametric_attention_with_residual_nonlinear(model, X, Y) -> Model:
|
|||
model.get_ref("norm_layer").set_dim("nI", tok2vec_width)
|
||||
model.get_ref("norm_layer").set_dim("nO", tok2vec_width)
|
||||
init_chain(model, X, Y)
|
||||
|
||||
|
||||
@registry.architectures("spacy.TextCatReduce.v1")
|
||||
def build_reduce_text_classifier(
|
||||
tok2vec: Model,
|
||||
exclusive_classes: bool,
|
||||
use_reduce_first: bool,
|
||||
use_reduce_last: bool,
|
||||
use_reduce_max: bool,
|
||||
use_reduce_mean: bool,
|
||||
nO: Optional[int] = None,
|
||||
) -> Model[List[Doc], Floats2d]:
|
||||
"""Build a model that classifies pooled `Doc` representations.
|
||||
|
||||
Pooling is performed using reductions. Reductions are concatenated when
|
||||
multiple reductions are used.
|
||||
|
||||
tok2vec (Model): the tok2vec layer to pool over.
|
||||
exclusive_classes (bool): Whether or not classes are mutually exclusive.
|
||||
use_reduce_first (bool): Pool by using the hidden representation of the
|
||||
first token of a `Doc`.
|
||||
use_reduce_last (bool): Pool by using the hidden representation of the
|
||||
last token of a `Doc`.
|
||||
use_reduce_max (bool): Pool by taking the maximum values of the hidden
|
||||
representations of a `Doc`.
|
||||
use_reduce_mean (bool): Pool by taking the mean of all hidden
|
||||
representations of a `Doc`.
|
||||
nO (Optional[int]): Number of classes.
|
||||
"""
|
||||
|
||||
fill_defaults = {"b": 0, "W": 0}
|
||||
reductions = []
|
||||
if use_reduce_first:
|
||||
reductions.append(reduce_first())
|
||||
if use_reduce_last:
|
||||
reductions.append(reduce_last())
|
||||
if use_reduce_max:
|
||||
reductions.append(reduce_max())
|
||||
if use_reduce_mean:
|
||||
reductions.append(reduce_mean())
|
||||
|
||||
if not len(reductions):
|
||||
raise ValueError(Errors.E1057)
|
||||
|
||||
with Model.define_operators({">>": chain}):
|
||||
cnn = tok2vec >> list2ragged() >> concatenate(*reductions)
|
||||
nO_tok2vec = tok2vec.maybe_get_dim("nO")
|
||||
nI = nO_tok2vec * len(reductions) if nO_tok2vec is not None else None
|
||||
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)
|
||||
if nO is not None:
|
||||
model.set_dim("nO", cast(int, nO))
|
||||
model.attrs["multi_label"] = not exclusive_classes
|
||||
return model
|
||||
|
|
|
|||
|
|
@ -55,8 +55,12 @@ no_output_layer = false
|
|||
|
||||
single_label_cnn_config = """
|
||||
[model]
|
||||
@architectures = "spacy.TextCatCNN.v2"
|
||||
@architectures = "spacy.TextCatReduce.v1"
|
||||
exclusive_classes = true
|
||||
use_reduce_first = false
|
||||
use_reduce_last = false
|
||||
use_reduce_max = false
|
||||
use_reduce_mean = true
|
||||
|
||||
[model.tok2vec]
|
||||
@architectures = "spacy.HashEmbedCNN.v2"
|
||||
|
|
|
|||
|
|
@ -53,8 +53,12 @@ no_output_layer = false
|
|||
|
||||
multi_label_cnn_config = """
|
||||
[model]
|
||||
@architectures = "spacy.TextCatCNN.v2"
|
||||
@architectures = "spacy.TextCatReduce.v1"
|
||||
exclusive_classes = false
|
||||
use_reduce_first = false
|
||||
use_reduce_last = false
|
||||
use_reduce_max = false
|
||||
use_reduce_mean = true
|
||||
|
||||
[model.tok2vec]
|
||||
@architectures = "spacy.HashEmbedCNN.v2"
|
||||
|
|
|
|||
|
|
@ -457,8 +457,8 @@ def test_no_resize(name, textcat_config):
|
|||
("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
|
||||
("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
|
||||
# CNN
|
||||
("textcat", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
|
||||
("textcat_multilabel", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
|
||||
("textcat", {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
|
||||
("textcat_multilabel", {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
|
||||
],
|
||||
)
|
||||
# fmt: on
|
||||
|
|
@ -485,9 +485,9 @@ def test_resize(name, textcat_config):
|
|||
("textcat", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "no_output_layer": True, "ngram_size": 3}),
|
||||
("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": False, "ngram_size": 3}),
|
||||
("textcat_multilabel", {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "no_output_layer": True, "ngram_size": 3}),
|
||||
# CNN
|
||||
("textcat", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
|
||||
("textcat_multilabel", {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
|
||||
# REDUCE
|
||||
("textcat", {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
|
||||
("textcat_multilabel", {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
|
||||
],
|
||||
)
|
||||
# fmt: on
|
||||
|
|
@ -701,12 +701,15 @@ def test_overfitting_IO_multi():
|
|||
# ENSEMBLE V2
|
||||
("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": False, "ngram_size": 1, "no_output_layer": False}}),
|
||||
("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatEnsemble.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "linear_model": {"@architectures": "spacy.TextCatBOW.v3", "exclusive_classes": True, "ngram_size": 5, "no_output_layer": False}}),
|
||||
# CNN V2
|
||||
# CNN V2 (legacy)
|
||||
("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
|
||||
("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatCNN.v2", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
|
||||
# PARAMETRIC ATTENTION V1
|
||||
("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatParametricAttention.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True}),
|
||||
("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatParametricAttention.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False}),
|
||||
# REDUCE V1
|
||||
("textcat", TRAIN_DATA_SINGLE_LABEL, {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": True, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
|
||||
("textcat_multilabel", TRAIN_DATA_MULTI_LABEL, {"@architectures": "spacy.TextCatReduce.v1", "tok2vec": DEFAULT_TOK2VEC_MODEL, "exclusive_classes": False, "use_reduce_first": True, "use_reduce_last": True, "use_reduce_max": True, "use_reduce_mean": True}),
|
||||
],
|
||||
)
|
||||
# fmt: on
|
||||
|
|
|
|||
|
|
@ -26,6 +26,7 @@ from spacy.ml.models import (
|
|||
build_Tok2Vec_model,
|
||||
)
|
||||
from spacy.ml.staticvectors import StaticVectors
|
||||
from spacy.util import registry
|
||||
|
||||
|
||||
def get_textcat_bow_kwargs():
|
||||
|
|
@ -284,3 +285,17 @@ def test_spancat_model_forward_backward(nO=5):
|
|||
Y, backprop = model((docs, spans), is_train=True)
|
||||
assert Y.shape == (spans.dataXd.shape[0], nO)
|
||||
backprop(Y)
|
||||
|
||||
|
||||
def test_textcat_reduce_invalid_args():
|
||||
textcat_reduce = registry.architectures.get("spacy.TextCatReduce.v1")
|
||||
tok2vec = make_test_tok2vec()
|
||||
with pytest.raises(ValueError, match=r"must be used with at least one reduction"):
|
||||
textcat_reduce(
|
||||
tok2vec=tok2vec,
|
||||
exclusive_classes=False,
|
||||
use_reduce_first=False,
|
||||
use_reduce_last=False,
|
||||
use_reduce_max=False,
|
||||
use_reduce_mean=False,
|
||||
)
|
||||
|
|
|
|||
|
|
@ -125,7 +125,7 @@ class Doc:
|
|||
vector: Optional[Floats1d] = ...,
|
||||
alignment_mode: str = ...,
|
||||
span_id: Union[int, str] = ...,
|
||||
) -> Span: ...
|
||||
) -> Optional[Span]: ...
|
||||
def similarity(self, other: Union[Doc, Span, Token, Lexeme]) -> float: ...
|
||||
@property
|
||||
def has_vector(self) -> bool: ...
|
||||
|
|
@ -179,15 +179,13 @@ class Doc:
|
|||
self, path: Union[str, Path], *, exclude: Iterable[str] = ...
|
||||
) -> None: ...
|
||||
def from_disk(
|
||||
self, path: Union[str, Path], *, exclude: Union[List[str], Tuple[str]] = ...
|
||||
self, path: Union[str, Path], *, exclude: Iterable[str] = ...
|
||||
) -> Doc: ...
|
||||
def to_bytes(self, *, exclude: Union[List[str], Tuple[str]] = ...) -> bytes: ...
|
||||
def from_bytes(
|
||||
self, bytes_data: bytes, *, exclude: Union[List[str], Tuple[str]] = ...
|
||||
) -> Doc: ...
|
||||
def to_dict(self, *, exclude: Union[List[str], Tuple[str]] = ...) -> bytes: ...
|
||||
def to_bytes(self, *, exclude: Iterable[str] = ...) -> bytes: ...
|
||||
def from_bytes(self, bytes_data: bytes, *, exclude: Iterable[str] = ...) -> Doc: ...
|
||||
def to_dict(self, *, exclude: Iterable[str] = ...) -> Dict[str, Any]: ...
|
||||
def from_dict(
|
||||
self, msg: bytes, *, exclude: Union[List[str], Tuple[str]] = ...
|
||||
self, msg: Dict[str, Any], *, exclude: Iterable[str] = ...
|
||||
) -> Doc: ...
|
||||
def extend_tensor(self, tensor: Floats2d) -> None: ...
|
||||
def retokenize(self) -> Retokenizer: ...
|
||||
|
|
|
|||
|
|
@ -1326,7 +1326,7 @@ cdef class Doc:
|
|||
|
||||
path (str / Path): A path to a directory. Paths may be either
|
||||
strings or `Path`-like objects.
|
||||
exclude (list): String names of serialization fields to exclude.
|
||||
exclude (Iterable[str]): String names of serialization fields to exclude.
|
||||
RETURNS (Doc): The modified `Doc` object.
|
||||
|
||||
DOCS: https://spacy.io/api/doc#from_disk
|
||||
|
|
@ -1339,7 +1339,7 @@ cdef class Doc:
|
|||
def to_bytes(self, *, exclude=tuple()):
|
||||
"""Serialize, i.e. export the document contents to a binary string.
|
||||
|
||||
exclude (list): String names of serialization fields to exclude.
|
||||
exclude (Iterable[str]): String names of serialization fields to exclude.
|
||||
RETURNS (bytes): A losslessly serialized copy of the `Doc`, including
|
||||
all annotations.
|
||||
|
||||
|
|
@ -1351,7 +1351,7 @@ cdef class Doc:
|
|||
"""Deserialize, i.e. import the document contents from a binary string.
|
||||
|
||||
data (bytes): The string to load from.
|
||||
exclude (list): String names of serialization fields to exclude.
|
||||
exclude (Iterable[str]): String names of serialization fields to exclude.
|
||||
RETURNS (Doc): Itself.
|
||||
|
||||
DOCS: https://spacy.io/api/doc#from_bytes
|
||||
|
|
@ -1361,11 +1361,8 @@ cdef class Doc:
|
|||
def to_dict(self, *, exclude=tuple()):
|
||||
"""Export the document contents to a dictionary for serialization.
|
||||
|
||||
exclude (list): String names of serialization fields to exclude.
|
||||
RETURNS (bytes): A losslessly serialized copy of the `Doc`, including
|
||||
all annotations.
|
||||
|
||||
DOCS: https://spacy.io/api/doc#to_bytes
|
||||
exclude (Iterable[str]): String names of serialization fields to exclude.
|
||||
RETURNS (Dict[str, Any]): A dictionary representation of the `Doc`
|
||||
"""
|
||||
array_head = Doc._get_array_attrs()
|
||||
strings = set()
|
||||
|
|
@ -1411,13 +1408,11 @@ cdef class Doc:
|
|||
return util.to_dict(serializers, exclude)
|
||||
|
||||
def from_dict(self, msg, *, exclude=tuple()):
|
||||
"""Deserialize, i.e. import the document contents from a binary string.
|
||||
"""Deserialize the document contents from a dictionary representation.
|
||||
|
||||
data (bytes): The string to load from.
|
||||
exclude (list): String names of serialization fields to exclude.
|
||||
msg (Dict[str, Any]): The dictionary to load from.
|
||||
exclude (Iterable[str]): String names of serialization fields to exclude.
|
||||
RETURNS (Doc): Itself.
|
||||
|
||||
DOCS: https://spacy.io/api/doc#from_dict
|
||||
"""
|
||||
if self.length != 0:
|
||||
raise ValueError(Errors.E033.format(length=self.length))
|
||||
|
|
|
|||
|
|
@ -1018,46 +1018,6 @@ but used an internal `tok2vec` instead of taking it as argument:
|
|||
|
||||
</Accordion>
|
||||
|
||||
### spacy.TextCatCNN.v2 {id="TextCatCNN"}
|
||||
|
||||
> #### Example Config
|
||||
>
|
||||
> ```ini
|
||||
> [model]
|
||||
> @architectures = "spacy.TextCatCNN.v2"
|
||||
> exclusive_classes = false
|
||||
> nO = null
|
||||
>
|
||||
> [model.tok2vec]
|
||||
> @architectures = "spacy.HashEmbedCNN.v2"
|
||||
> pretrained_vectors = null
|
||||
> width = 96
|
||||
> depth = 4
|
||||
> embed_size = 2000
|
||||
> window_size = 1
|
||||
> maxout_pieces = 3
|
||||
> subword_features = true
|
||||
> ```
|
||||
|
||||
A neural network model where token vectors are calculated using a CNN. The
|
||||
vectors are mean pooled and used as features in a feed-forward network. This
|
||||
architecture is usually less accurate than the ensemble, but runs faster.
|
||||
|
||||
| Name | Description |
|
||||
| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~ |
|
||||
| `tok2vec` | The [`tok2vec`](#tok2vec) layer of the model. ~~Model~~ |
|
||||
| `nO` | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
|
||||
| **CREATES** | The model using the architecture. ~~Model[List[Doc], Floats2d]~~ |
|
||||
|
||||
<Accordion title="spacy.TextCatCNN.v1 definition" spaced>
|
||||
|
||||
[TextCatCNN.v1](/api/legacy#TextCatCNN_v1) had the exact same signature, but was
|
||||
not yet resizable. Since v2, new labels can be added to this component, even
|
||||
after training.
|
||||
|
||||
</Accordion>
|
||||
|
||||
### spacy.TextCatBOW.v3 {id="TextCatBOW"}
|
||||
|
||||
> #### Example Config
|
||||
|
|
@ -1134,6 +1094,54 @@ to attend to tokens that are relevant to text classification.
|
|||
| `nO` | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
|
||||
| **CREATES** | The model using the architecture. ~~Model[List[Doc], Floats2d]~~ |
|
||||
|
||||
### spacy.TextCatReduce.v1 {id="TextCatReduce"}
|
||||
|
||||
> #### Example Config
|
||||
>
|
||||
> ```ini
|
||||
> [model]
|
||||
> @architectures = "spacy.TextCatReduce.v1"
|
||||
> exclusive_classes = false
|
||||
> use_reduce_first = false
|
||||
> use_reduce_last = false
|
||||
> use_reduce_max = false
|
||||
> use_reduce_mean = true
|
||||
> nO = null
|
||||
>
|
||||
> [model.tok2vec]
|
||||
> @architectures = "spacy.HashEmbedCNN.v2"
|
||||
> pretrained_vectors = null
|
||||
> width = 96
|
||||
> depth = 4
|
||||
> embed_size = 2000
|
||||
> window_size = 1
|
||||
> maxout_pieces = 3
|
||||
> subword_features = true
|
||||
> ```
|
||||
|
||||
A classifier that pools token hidden representations of each `Doc` using first,
|
||||
max or mean reduction and then applies a classification layer. Reductions are
|
||||
concatenated when multiple reductions are used.
|
||||
|
||||
<Infobox variant="warning" title="Relation to TextCatCNN" id="TextCatCNN">
|
||||
|
||||
`TextCatReduce` is a generalization of the older
|
||||
[`TextCatCNN`](/api/legacy#TextCatCNN_v2) model. `TextCatCNN` always uses a mean
|
||||
reduction, whereas `TextCatReduce` also supports first/max reductions.
|
||||
|
||||
</Infobox>
|
||||
|
||||
| Name | Description |
|
||||
| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~ |
|
||||
| `tok2vec` | The [`tok2vec`](#tok2vec) layer of the model. ~~Model~~ |
|
||||
| `use_reduce_first` | Pool by using the hidden representation of the first token of a `Doc`. ~~bool~~ |
|
||||
| `use_reduce_last` | Pool by using the hidden representation of the last token of a `Doc`. ~~bool~~ |
|
||||
| `use_reduce_max` | Pool by taking the maximum values of the hidden representations of a `Doc`. ~~bool~~ |
|
||||
| `use_reduce_mean` | Pool by taking the mean of all hidden representations of a `Doc`. ~~bool~~ |
|
||||
| `nO` | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
|
||||
| **CREATES** | The model using the architecture. ~~Model[List[Doc], Floats2d]~~ |
|
||||
|
||||
## Span classification architectures {id="spancat",source="spacy/ml/models/spancat.py"}
|
||||
|
||||
### spacy.SpanCategorizer.v1 {id="SpanCategorizer"}
|
||||
|
|
|
|||
|
|
@ -162,7 +162,10 @@ network has an internal CNN Tok2Vec layer and uses attention.
|
|||
|
||||
Since `spacy.TextCatCNN.v2`, this architecture has become resizable, which means
|
||||
that you can add labels to a previously trained textcat. `TextCatCNN` v1 did not
|
||||
yet support that.
|
||||
yet support that. `TextCatCNN` has been replaced by the more general
|
||||
[`TextCatReduce`](/api/architectures#TextCatReduce) layer. `TextCatCNN` is
|
||||
identical to `TextCatReduce` with `use_reduce_mean=true`,
|
||||
`use_reduce_first=false`, `reduce_last=false` and `use_reduce_max=false`.
|
||||
|
||||
> #### Example Config
|
||||
>
|
||||
|
|
@ -194,6 +197,51 @@ architecture is usually less accurate than the ensemble, but runs faster.
|
|||
| `nO` | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
|
||||
| **CREATES** | The model using the architecture. ~~Model[List[Doc], Floats2d]~~ |
|
||||
|
||||
### spacy.TextCatCNN.v2 {id="TextCatCNN_v2"}
|
||||
|
||||
> #### Example Config
|
||||
>
|
||||
> ```ini
|
||||
> [model]
|
||||
> @architectures = "spacy.TextCatCNN.v2"
|
||||
> exclusive_classes = false
|
||||
> nO = null
|
||||
>
|
||||
> [model.tok2vec]
|
||||
> @architectures = "spacy.HashEmbedCNN.v2"
|
||||
> pretrained_vectors = null
|
||||
> width = 96
|
||||
> depth = 4
|
||||
> embed_size = 2000
|
||||
> window_size = 1
|
||||
> maxout_pieces = 3
|
||||
> subword_features = true
|
||||
> ```
|
||||
|
||||
A neural network model where token vectors are calculated using a CNN. The
|
||||
vectors are mean pooled and used as features in a feed-forward network. This
|
||||
architecture is usually less accurate than the ensemble, but runs faster.
|
||||
|
||||
`TextCatCNN` has been replaced by the more general
|
||||
[`TextCatReduce`](/api/architectures#TextCatReduce) layer. `TextCatCNN` is
|
||||
identical to `TextCatReduce` with `use_reduce_mean=true`,
|
||||
`use_reduce_first=false`, `reduce_last=false` and `use_reduce_max=false`.
|
||||
|
||||
| Name | Description |
|
||||
| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~ |
|
||||
| `tok2vec` | The [`tok2vec`](#tok2vec) layer of the model. ~~Model~~ |
|
||||
| `nO` | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `initialize` is called. ~~Optional[int]~~ |
|
||||
| **CREATES** | The model using the architecture. ~~Model[List[Doc], Floats2d]~~ |
|
||||
|
||||
<Accordion title="spacy.TextCatCNN.v1 definition" spaced>
|
||||
|
||||
[TextCatCNN.v1](/api/legacy#TextCatCNN_v1) had the exact same signature, but was
|
||||
not yet resizable. Since v2, new labels can be added to this component, even
|
||||
after training.
|
||||
|
||||
</Accordion>
|
||||
|
||||
### spacy.TextCatBOW.v1 {id="TextCatBOW_v1"}
|
||||
|
||||
Since `spacy.TextCatBOW.v2`, this architecture has become resizable, which means
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user