mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-13 13:17:06 +03:00
7f5715a081
* setting KB in the EL constructor, similar to how the model is passed on * removing wikipedia example files - moved to projects * throw an error when nlp.update is called with 2 positional arguments * rewriting the config logic in create pipe to accomodate for other objects (e.g. KB) in the config * update config files with new parameters * avoid training pipeline components that don't have a model (like sentencizer) * various small fixes + UX improvements * small fixes * set thinc to 8.0.0a9 everywhere * remove outdated comment
68 lines
1.4 KiB
INI
68 lines
1.4 KiB
INI
[training]
|
|
use_gpu = -1
|
|
limit = 0
|
|
dropout = 0.2
|
|
patience = 10000
|
|
eval_frequency = 200
|
|
scores = ["ents_f"]
|
|
score_weights = {"ents_f": 1}
|
|
orth_variant_level = 0.0
|
|
gold_preproc = true
|
|
max_length = 0
|
|
batch_size = 25
|
|
seed = 0
|
|
accumulate_gradient = 2
|
|
|
|
[optimizer]
|
|
@optimizers = "Adam.v1"
|
|
learn_rate = 0.001
|
|
beta1 = 0.9
|
|
beta2 = 0.999
|
|
|
|
[nlp]
|
|
lang = "en"
|
|
vectors = null
|
|
|
|
[nlp.pipeline.tok2vec]
|
|
factory = "tok2vec"
|
|
|
|
[nlp.pipeline.tok2vec.model]
|
|
@architectures = "spacy.Tok2Vec.v1"
|
|
|
|
[nlp.pipeline.tok2vec.model.extract]
|
|
@architectures = "spacy.CharacterEmbed.v1"
|
|
width = 96
|
|
nM = 64
|
|
nC = 8
|
|
rows = 2000
|
|
columns = ["ID", "NORM", "PREFIX", "SUFFIX", "SHAPE", "ORTH"]
|
|
|
|
[nlp.pipeline.tok2vec.model.extract.features]
|
|
@architectures = "spacy.Doc2Feats.v1"
|
|
columns = ${nlp.pipeline.tok2vec.model.extract:columns}
|
|
|
|
[nlp.pipeline.tok2vec.model.embed]
|
|
@architectures = "spacy.LayerNormalizedMaxout.v1"
|
|
width = ${nlp.pipeline.tok2vec.model.extract:width}
|
|
maxout_pieces = 4
|
|
|
|
[nlp.pipeline.tok2vec.model.encode]
|
|
@architectures = "spacy.MaxoutWindowEncoder.v1"
|
|
width = ${nlp.pipeline.tok2vec.model.extract:width}
|
|
window_size = 1
|
|
maxout_pieces = 2
|
|
depth = 2
|
|
|
|
[nlp.pipeline.ner]
|
|
factory = "ner"
|
|
|
|
[nlp.pipeline.ner.model]
|
|
@architectures = "spacy.TransitionBasedParser.v1"
|
|
nr_feature_tokens = 6
|
|
hidden_width = 64
|
|
maxout_pieces = 2
|
|
|
|
[nlp.pipeline.ner.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecTensors.v1"
|
|
width = ${nlp.pipeline.tok2vec.model.extract:width}
|