explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-14 03:26:24 +03:00
Code Issues Packages Projects Releases Wiki Activity

Remove vector pruning arg from train CLI

Browse Source
This commit is contained in:
Matthew Honnibal 2017-10-31 19:21:05 +01:00
parent 59203a2e8a
commit 3659a807b0
1 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/cli/train.py
View File

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