mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +03:00
cd6bd91c3a
The behavior of `spacy.Corpus.v1` is unexpected enough for `max_length != 0` that `0` is a better default for users creating a new config with the quickstart. If not, documents are skipped, sometimes the entire corpus is skipped, and sometimes documents are (quite unexpectedly for your average user) split into sentences.
425 lines
10 KiB
Django/Jinja
425 lines
10 KiB
Django/Jinja
{# This is a template for training configs used for the quickstart widget in
|
|
the docs and the init config command. It encodes various best practices and
|
|
can help generate the best possible configuration, given a user's requirements. #}
|
|
{%- set use_transformer = hardware != "cpu" -%}
|
|
{%- set transformer = transformer_data[optimize] if use_transformer else {} -%}
|
|
[paths]
|
|
train = null
|
|
dev = null
|
|
|
|
[system]
|
|
{% if use_transformer -%}
|
|
gpu_allocator = "pytorch"
|
|
{% else -%}
|
|
gpu_allocator = null
|
|
{% endif %}
|
|
|
|
[nlp]
|
|
lang = "{{ lang }}"
|
|
{%- if "tagger" in components or "morphologizer" in components or "parser" in components or "ner" in components or "entity_linker" in components or (("textcat" in components or "textcat_multilabel" in components) and optimize == "accuracy") -%}
|
|
{%- set full_pipeline = ["transformer" if use_transformer else "tok2vec"] + components %}
|
|
{%- else -%}
|
|
{%- set full_pipeline = components %}
|
|
{%- endif %}
|
|
pipeline = {{ full_pipeline|pprint()|replace("'", '"')|safe }}
|
|
batch_size = {{ 128 if hardware == "gpu" else 1000 }}
|
|
|
|
[components]
|
|
|
|
{# TRANSFORMER PIPELINE #}
|
|
{%- if use_transformer -%}
|
|
[components.transformer]
|
|
factory = "transformer"
|
|
|
|
[components.transformer.model]
|
|
@architectures = "spacy-transformers.TransformerModel.v1"
|
|
name = "{{ transformer["name"] }}"
|
|
tokenizer_config = {"use_fast": true}
|
|
|
|
[components.transformer.model.get_spans]
|
|
@span_getters = "spacy-transformers.strided_spans.v1"
|
|
window = 128
|
|
stride = 96
|
|
|
|
{% if "morphologizer" in components %}
|
|
[components.morphologizer]
|
|
factory = "morphologizer"
|
|
|
|
[components.morphologizer.model]
|
|
@architectures = "spacy.Tagger.v1"
|
|
nO = null
|
|
|
|
[components.morphologizer.model.tok2vec]
|
|
@architectures = "spacy-transformers.TransformerListener.v1"
|
|
grad_factor = 1.0
|
|
|
|
[components.morphologizer.model.tok2vec.pooling]
|
|
@layers = "reduce_mean.v1"
|
|
{%- endif %}
|
|
|
|
{% if "tagger" in components %}
|
|
[components.tagger]
|
|
factory = "tagger"
|
|
|
|
[components.tagger.model]
|
|
@architectures = "spacy.Tagger.v1"
|
|
nO = null
|
|
|
|
[components.tagger.model.tok2vec]
|
|
@architectures = "spacy-transformers.TransformerListener.v1"
|
|
grad_factor = 1.0
|
|
|
|
[components.tagger.model.tok2vec.pooling]
|
|
@layers = "reduce_mean.v1"
|
|
{%- endif %}
|
|
|
|
{% if "parser" in components -%}
|
|
[components.parser]
|
|
factory = "parser"
|
|
|
|
[components.parser.model]
|
|
@architectures = "spacy.TransitionBasedParser.v2"
|
|
state_type = "parser"
|
|
extra_state_tokens = false
|
|
hidden_width = 128
|
|
maxout_pieces = 3
|
|
use_upper = false
|
|
nO = null
|
|
|
|
[components.parser.model.tok2vec]
|
|
@architectures = "spacy-transformers.TransformerListener.v1"
|
|
grad_factor = 1.0
|
|
|
|
[components.parser.model.tok2vec.pooling]
|
|
@layers = "reduce_mean.v1"
|
|
{%- endif %}
|
|
|
|
{% if "ner" in components -%}
|
|
[components.ner]
|
|
factory = "ner"
|
|
|
|
[components.ner.model]
|
|
@architectures = "spacy.TransitionBasedParser.v2"
|
|
state_type = "ner"
|
|
extra_state_tokens = false
|
|
hidden_width = 64
|
|
maxout_pieces = 2
|
|
use_upper = false
|
|
nO = null
|
|
|
|
[components.ner.model.tok2vec]
|
|
@architectures = "spacy-transformers.TransformerListener.v1"
|
|
grad_factor = 1.0
|
|
|
|
[components.ner.model.tok2vec.pooling]
|
|
@layers = "reduce_mean.v1"
|
|
{% endif -%}
|
|
|
|
{% if "entity_linker" in components -%}
|
|
[components.entity_linker]
|
|
factory = "entity_linker"
|
|
get_candidates = {"@misc":"spacy.CandidateGenerator.v1"}
|
|
incl_context = true
|
|
incl_prior = true
|
|
|
|
[components.entity_linker.model]
|
|
@architectures = "spacy.EntityLinker.v1"
|
|
nO = null
|
|
|
|
[components.entity_linker.model.tok2vec]
|
|
@architectures = "spacy-transformers.TransformerListener.v1"
|
|
grad_factor = 1.0
|
|
|
|
[components.entity_linker.model.tok2vec.pooling]
|
|
@layers = "reduce_mean.v1"
|
|
{% endif -%}
|
|
|
|
{% if "textcat" in components %}
|
|
[components.textcat]
|
|
factory = "textcat"
|
|
|
|
{% if optimize == "accuracy" %}
|
|
[components.textcat.model]
|
|
@architectures = "spacy.TextCatEnsemble.v2"
|
|
nO = null
|
|
|
|
[components.textcat.model.tok2vec]
|
|
@architectures = "spacy-transformers.TransformerListener.v1"
|
|
grad_factor = 1.0
|
|
|
|
[components.textcat.model.tok2vec.pooling]
|
|
@layers = "reduce_mean.v1"
|
|
|
|
[components.textcat.model.linear_model]
|
|
@architectures = "spacy.TextCatBOW.v1"
|
|
exclusive_classes = true
|
|
ngram_size = 1
|
|
no_output_layer = false
|
|
|
|
{% else -%}
|
|
[components.textcat.model]
|
|
@architectures = "spacy.TextCatBOW.v1"
|
|
exclusive_classes = true
|
|
ngram_size = 1
|
|
no_output_layer = false
|
|
{%- endif %}
|
|
{%- endif %}
|
|
|
|
{% if "textcat_multilabel" in components %}
|
|
[components.textcat_multilabel]
|
|
factory = "textcat_multilabel"
|
|
|
|
{% if optimize == "accuracy" %}
|
|
[components.textcat_multilabel.model]
|
|
@architectures = "spacy.TextCatEnsemble.v2"
|
|
nO = null
|
|
|
|
[components.textcat_multilabel.model.tok2vec]
|
|
@architectures = "spacy-transformers.TransformerListener.v1"
|
|
grad_factor = 1.0
|
|
|
|
[components.textcat_multilabel.model.tok2vec.pooling]
|
|
@layers = "reduce_mean.v1"
|
|
|
|
[components.textcat_multilabel.model.linear_model]
|
|
@architectures = "spacy.TextCatBOW.v1"
|
|
exclusive_classes = false
|
|
ngram_size = 1
|
|
no_output_layer = false
|
|
|
|
{% else -%}
|
|
[components.textcat_multilabel.model]
|
|
@architectures = "spacy.TextCatBOW.v1"
|
|
exclusive_classes = false
|
|
ngram_size = 1
|
|
no_output_layer = false
|
|
{%- endif %}
|
|
{%- endif %}
|
|
|
|
{# NON-TRANSFORMER PIPELINE #}
|
|
{% else -%}
|
|
|
|
[components.tok2vec]
|
|
factory = "tok2vec"
|
|
|
|
[components.tok2vec.model]
|
|
@architectures = "spacy.Tok2Vec.v2"
|
|
|
|
[components.tok2vec.model.embed]
|
|
@architectures = "spacy.MultiHashEmbed.v2"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
{% if has_letters -%}
|
|
attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE"]
|
|
rows = [5000, 2500, 2500, 2500]
|
|
{% else -%}
|
|
attrs = ["ORTH", "SHAPE"]
|
|
rows = [5000, 2500]
|
|
{% endif -%}
|
|
include_static_vectors = {{ "true" if optimize == "accuracy" else "false" }}
|
|
|
|
[components.tok2vec.model.encode]
|
|
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
|
width = {{ 96 if optimize == "efficiency" else 256 }}
|
|
depth = {{ 4 if optimize == "efficiency" else 8 }}
|
|
window_size = 1
|
|
maxout_pieces = 3
|
|
|
|
{% if "morphologizer" in components %}
|
|
[components.morphologizer]
|
|
factory = "morphologizer"
|
|
|
|
[components.morphologizer.model]
|
|
@architectures = "spacy.Tagger.v1"
|
|
nO = null
|
|
|
|
[components.morphologizer.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
{%- endif %}
|
|
|
|
{% if "tagger" in components %}
|
|
[components.tagger]
|
|
factory = "tagger"
|
|
|
|
[components.tagger.model]
|
|
@architectures = "spacy.Tagger.v1"
|
|
nO = null
|
|
|
|
[components.tagger.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
{%- endif %}
|
|
|
|
{% if "parser" in components -%}
|
|
[components.parser]
|
|
factory = "parser"
|
|
|
|
[components.parser.model]
|
|
@architectures = "spacy.TransitionBasedParser.v2"
|
|
state_type = "parser"
|
|
extra_state_tokens = false
|
|
hidden_width = 128
|
|
maxout_pieces = 3
|
|
use_upper = true
|
|
nO = null
|
|
|
|
[components.parser.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
{%- endif %}
|
|
|
|
{% if "ner" in components %}
|
|
[components.ner]
|
|
factory = "ner"
|
|
|
|
[components.ner.model]
|
|
@architectures = "spacy.TransitionBasedParser.v2"
|
|
state_type = "ner"
|
|
extra_state_tokens = false
|
|
hidden_width = 64
|
|
maxout_pieces = 2
|
|
use_upper = true
|
|
nO = null
|
|
|
|
[components.ner.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
{% endif %}
|
|
|
|
{% if "entity_linker" in components -%}
|
|
[components.entity_linker]
|
|
factory = "entity_linker"
|
|
get_candidates = {"@misc":"spacy.CandidateGenerator.v1"}
|
|
incl_context = true
|
|
incl_prior = true
|
|
|
|
[components.entity_linker.model]
|
|
@architectures = "spacy.EntityLinker.v1"
|
|
nO = null
|
|
|
|
[components.entity_linker.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
{% endif %}
|
|
|
|
{% if "textcat" in components %}
|
|
[components.textcat]
|
|
factory = "textcat"
|
|
|
|
{% if optimize == "accuracy" %}
|
|
[components.textcat.model]
|
|
@architectures = "spacy.TextCatEnsemble.v2"
|
|
nO = null
|
|
|
|
[components.textcat.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
|
|
[components.textcat.model.linear_model]
|
|
@architectures = "spacy.TextCatBOW.v1"
|
|
exclusive_classes = true
|
|
ngram_size = 1
|
|
no_output_layer = false
|
|
|
|
{% else -%}
|
|
[components.textcat.model]
|
|
@architectures = "spacy.TextCatBOW.v1"
|
|
exclusive_classes = true
|
|
ngram_size = 1
|
|
no_output_layer = false
|
|
{%- endif %}
|
|
{%- endif %}
|
|
|
|
{% if "textcat_multilabel" in components %}
|
|
[components.textcat_multilabel]
|
|
factory = "textcat_multilabel"
|
|
|
|
{% if optimize == "accuracy" %}
|
|
[components.textcat_multilabel.model]
|
|
@architectures = "spacy.TextCatEnsemble.v2"
|
|
nO = null
|
|
|
|
[components.textcat_multilabel.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
|
|
[components.textcat_multilabel.model.linear_model]
|
|
@architectures = "spacy.TextCatBOW.v1"
|
|
exclusive_classes = false
|
|
ngram_size = 1
|
|
no_output_layer = false
|
|
|
|
{% else -%}
|
|
[components.textcat_multilabel.model]
|
|
@architectures = "spacy.TextCatBOW.v1"
|
|
exclusive_classes = false
|
|
ngram_size = 1
|
|
no_output_layer = false
|
|
{%- endif %}
|
|
{%- endif %}
|
|
{% endif %}
|
|
|
|
{% for pipe in components %}
|
|
{% if pipe not in ["tagger", "morphologizer", "parser", "ner", "textcat", "textcat_multilabel", "entity_linker"] %}
|
|
{# Other components defined by the user: we just assume they're factories #}
|
|
[components.{{ pipe }}]
|
|
factory = "{{ pipe }}"
|
|
{% endif %}
|
|
{% endfor %}
|
|
|
|
[corpora]
|
|
|
|
[corpora.train]
|
|
@readers = "spacy.Corpus.v1"
|
|
path = ${paths.train}
|
|
max_length = 0
|
|
|
|
[corpora.dev]
|
|
@readers = "spacy.Corpus.v1"
|
|
path = ${paths.dev}
|
|
max_length = 0
|
|
|
|
[training]
|
|
{% if use_transformer -%}
|
|
accumulate_gradient = {{ transformer["size_factor"] }}
|
|
{% endif -%}
|
|
dev_corpus = "corpora.dev"
|
|
train_corpus = "corpora.train"
|
|
|
|
[training.optimizer]
|
|
@optimizers = "Adam.v1"
|
|
|
|
{% if use_transformer -%}
|
|
[training.optimizer.learn_rate]
|
|
@schedules = "warmup_linear.v1"
|
|
warmup_steps = 250
|
|
total_steps = 20000
|
|
initial_rate = 5e-5
|
|
{% endif %}
|
|
|
|
{% if use_transformer %}
|
|
[training.batcher]
|
|
@batchers = "spacy.batch_by_padded.v1"
|
|
discard_oversize = true
|
|
size = 2000
|
|
buffer = 256
|
|
{%- else %}
|
|
[training.batcher]
|
|
@batchers = "spacy.batch_by_words.v1"
|
|
discard_oversize = false
|
|
tolerance = 0.2
|
|
|
|
[training.batcher.size]
|
|
@schedules = "compounding.v1"
|
|
start = 100
|
|
stop = 1000
|
|
compound = 1.001
|
|
{% endif %}
|
|
|
|
[initialize]
|
|
{% if use_transformer or optimize == "efficiency" or not word_vectors -%}
|
|
vectors = null
|
|
{% else -%}
|
|
vectors = "{{ word_vectors }}"
|
|
{% endif -%}
|