explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 01:48:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

Also rename to include_static_vectors in CharEmbed

Browse Source
This commit is contained in:
Adriane Boyd 2020-10-09 11:54:48 +02:00
parent 67652bcbb5
commit 39aabf50ab
3 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/ml/models/tok2vec.py
View File

@ -177,7 +177,7 @@ def CharacterEmbed(
rows: int, rows: int,
nM: int, nM: int,
nC: int, nC: int,
also_use_static_vectors: bool, include_static_vectors: bool,
feature: Union[int, str] = "LOWER", feature: Union[int, str] = "LOWER",
) -> Model[List[Doc], List[Floats2d]]: ) -> Model[List[Doc], List[Floats2d]]:
"""Construct an embedded representation based on character embeddings, using """Construct an embedded representation based on character embeddings, using
@ -204,13 +204,13 @@ def CharacterEmbed(
nC (int): The number of UTF-8 bytes to embed per word. Recommended values nC (int): The number of UTF-8 bytes to embed per word. Recommended values
are between 3 and 8, although it may depend on the length of words in the are between 3 and 8, although it may depend on the length of words in the
language. language.
also_use_static_vectors (bool): Whether to also use static word vectors. include_static_vectors (bool): Whether to also use static word vectors.
Requires a vectors table to be loaded in the Doc objects' vocab. Requires a vectors table to be loaded in the Doc objects' vocab.
""" """
feature = intify_attr(feature) feature = intify_attr(feature)
if feature is None: if feature is None:
raise ValueError(Errors.E911(feat=feature)) raise ValueError(Errors.E911(feat=feature))
if also_use_static_vectors: if include_static_vectors:
model = chain( model = chain(
concatenate( concatenate(
chain(_character_embed.CharacterEmbed(nM=nM, nC=nC), list2ragged()), chain(_character_embed.CharacterEmbed(nM=nM, nC=nC), list2ragged()),

2
spacy/pipeline/morphologizer.pyx
View File

@ -32,7 +32,7 @@ width = 128
rows = 7000 rows = 7000
nM = 64 nM = 64
nC = 8 nC = 8
also_use_static_vectors = false include_static_vectors = false
[model.tok2vec.encode] [model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v1" @architectures = "spacy.MaxoutWindowEncoder.v1"

4
spacy/tests/pipeline/test_tok2vec.py
View File

@ -63,8 +63,8 @@ def test_tok2vec_batch_sizes(batch_size, width, embed_size):
[ [
(8, MultiHashEmbed, {"rows": [100, 100], "attrs": ["SHAPE", "LOWER"], "include_static_vectors": False}, MaxoutWindowEncoder, {"window_size": 1, "maxout_pieces": 3, "depth": 2}), (8, MultiHashEmbed, {"rows": [100, 100], "attrs": ["SHAPE", "LOWER"], "include_static_vectors": False}, MaxoutWindowEncoder, {"window_size": 1, "maxout_pieces": 3, "depth": 2}),
(8, MultiHashEmbed, {"rows": [100, 20], "attrs": ["ORTH", "PREFIX"], "include_static_vectors": False}, MishWindowEncoder, {"window_size": 1, "depth": 6}), (8, MultiHashEmbed, {"rows": [100, 20], "attrs": ["ORTH", "PREFIX"], "include_static_vectors": False}, MishWindowEncoder, {"window_size": 1, "depth": 6}),
(8, CharacterEmbed, {"rows": 100, "nM": 64, "nC": 8, "also_use_static_vectors": False}, MaxoutWindowEncoder, {"window_size": 1, "maxout_pieces": 3, "depth": 3}), (8, CharacterEmbed, {"rows": 100, "nM": 64, "nC": 8, "include_static_vectors": False}, MaxoutWindowEncoder, {"window_size": 1, "maxout_pieces": 3, "depth": 3}),
(8, CharacterEmbed, {"rows": 100, "nM": 16, "nC": 2, "also_use_static_vectors": False}, MishWindowEncoder, {"window_size": 1, "depth": 3}), (8, CharacterEmbed, {"rows": 100, "nM": 16, "nC": 2, "include_static_vectors": False}, MishWindowEncoder, {"window_size": 1, "depth": 3}),
], ],
) )
# fmt: on # fmt: on