explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 00:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add -prune-vectors argument to spacy.cly.train

Browse Source
This commit is contained in:
Matthew Honnibal 2017-10-30 18:00:10 +01:00
parent e026b29ea9
commit e98451b5f7
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/cli/train.py
View File

@ -32,6 +32,7 @@ numpy.random.seed(0)
n_sents=("number of sentences", "option", "ns", int),
use_gpu=("Use GPU", "option", "g", int),
vectors=("Model to load vectors from", "option", "v"),
vectors_limit=("Truncate to N vectors (requires -v)", "option", None, int),
no_tagger=("Don't train tagger", "flag", "T", bool),
no_parser=("Don't train parser", "flag", "P", bool),
no_entities=("Don't train NER", "flag", "N", bool),
@ -40,9 +41,9 @@ numpy.random.seed(0)
meta_path=("Optional path to meta.json. All relevant properties will be "
"overwritten.", "option", "m", Path))
def train(cmd, lang, output_dir, train_data, dev_data, n_iter=30, n_sents=0,
use_gpu=-1, vectors=None, no_tagger=False, no_parser=False,
no_entities=False, gold_preproc=False, version="0.0.0",
meta_path=None):
use_gpu=-1, vectors=None, vectors_limit=None, no_tagger=False,
no_parser=False, no_entities=False, gold_preproc=False,
version="0.0.0", meta_path=None):
"""
Train a model. Expects data in spaCy's JSON format.
"""
@ -94,6 +95,8 @@ def train(cmd, lang, output_dir, train_data, dev_data, n_iter=30, n_sents=0,
nlp.meta.update(meta)
if vectors:
util.load_model(vectors, vocab=nlp.vocab)
if vectors_limit is not None:
nlp.vocab.prune_vectors(vectors_limit)
for name in pipeline:
nlp.add_pipe(nlp.create_pipe(name), name=name)
optimizer = nlp.begin_training(lambda: corpus.train_tuples, device=use_gpu)