mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-01 00:17:44 +03:00
ecb3c4e8f4
* Move batchers into their own module (and registry) * Update CLI * Update Corpus and batcher * Update tests * Update one config * Merge 'evaluation' block back under [training] * Import batchers in gold __init__ * Fix batchers * Update config * Update schema * Update util * Don't assume train and dev are actually paths * Update onto-joint config * Fix missing import * Format * Format * Update spacy/gold/corpus.py Co-authored-by: Ines Montani <ines@ines.io> * Fix name * Update default config * Fix get_length option in batchers * Update test * Add comment * Pass path into Corpus * Update docstring * Update schema and configs * Update config * Fix test * Fix paths * Fix print * Fix create_train_batches * [training.read_train] -> [training.train_corpus] * Update onto-joint config Co-authored-by: Ines Montani <ines@ines.io>
111 lines
2.1 KiB
INI
111 lines
2.1 KiB
INI
[paths]
|
|
train = ""
|
|
dev = ""
|
|
raw = null
|
|
init_tok2vec = null
|
|
|
|
[system]
|
|
seed = 0
|
|
use_pytorch_for_gpu_memory = false
|
|
|
|
[training]
|
|
seed = ${system:seed}
|
|
dropout = 0.2
|
|
init_tok2vec = ${paths:init_tok2vec}
|
|
vectors = null
|
|
accumulate_gradient = 1
|
|
max_steps = 0
|
|
max_epochs = 0
|
|
patience = 10000
|
|
eval_frequency = 200
|
|
score_weights = {"dep_las": 0.8, "tag_acc": 0.2}
|
|
|
|
[training.read_train]
|
|
@readers = "spacy.Corpus.v1"
|
|
path = ${paths:train}
|
|
gold_preproc = true
|
|
max_length = 0
|
|
limit = 0
|
|
|
|
[training.read_dev]
|
|
@readers = "spacy.Corpus.v1"
|
|
path = ${paths:dev}
|
|
gold_preproc = ${training.read_train:gold_preproc}
|
|
max_length = 0
|
|
limit = 0
|
|
|
|
[training.batcher]
|
|
@batchers = "batch_by_words.v1"
|
|
discard_oversize = false
|
|
tolerance = 0.2
|
|
|
|
[training.batcher.size]
|
|
@schedules = "compounding.v1"
|
|
start = 100
|
|
stop = 1000
|
|
compound = 1.001
|
|
|
|
[training.optimizer]
|
|
@optimizers = "Adam.v1"
|
|
learn_rate = 0.001
|
|
beta1 = 0.9
|
|
beta2 = 0.999
|
|
|
|
[nlp]
|
|
lang = "en"
|
|
pipeline = ["tok2vec", "tagger", "parser"]
|
|
load_vocab_data = false
|
|
|
|
[nlp.tokenizer]
|
|
@tokenizers = "spacy.Tokenizer.v1"
|
|
|
|
[nlp.lemmatizer]
|
|
@lemmatizers = "spacy.Lemmatizer.v1"
|
|
|
|
[components]
|
|
|
|
[components.tok2vec]
|
|
factory = "tok2vec"
|
|
|
|
[components.tagger]
|
|
factory = "tagger"
|
|
|
|
[components.parser]
|
|
factory = "parser"
|
|
learn_tokens = false
|
|
min_action_freq = 1
|
|
|
|
[components.tagger.model]
|
|
@architectures = "spacy.Tagger.v1"
|
|
|
|
[components.tagger.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode:width}
|
|
|
|
[components.parser.model]
|
|
@architectures = "spacy.TransitionBasedParser.v1"
|
|
nr_feature_tokens = 8
|
|
hidden_width = 64
|
|
maxout_pieces = 3
|
|
|
|
[components.parser.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode:width}
|
|
|
|
[components.tok2vec.model]
|
|
@architectures = "spacy.Tok2Vec.v1"
|
|
|
|
[components.tok2vec.model.embed]
|
|
@architectures = "spacy.MultiHashEmbed.v1"
|
|
width = ${components.tok2vec.model.encode:width}
|
|
rows = 2000
|
|
also_embed_subwords = true
|
|
also_use_static_vectors = false
|
|
|
|
[components.tok2vec.model.encode]
|
|
@architectures = "spacy.MaxoutWindowEncoder.v1"
|
|
width = 96
|
|
depth = 4
|
|
window_size = 1
|
|
maxout_pieces = 3
|