explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-03-03 19:08:06 +03:00
Code Issues Packages Projects Releases Wiki Activity

Improve output on trainer

Browse Source
This commit is contained in:
Matthew Honnibal 2017-03-11 11:12:48 -06:00
parent b438dfd3f3
commit 1224c4d3c6
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
spacy/train.py
View File

@ -2,6 +2,7 @@ from __future__ import absolute_import
from __future__ import unicode_literals from __future__ import unicode_literals
import random import random
import tqdm
from .gold import GoldParse from .gold import GoldParse
from .scorer import Scorer from .scorer import Scorer
from .gold import merge_sents from .gold import merge_sents
@ -12,11 +13,12 @@ class Trainer(object):
def __init__(self, nlp, gold_tuples): def __init__(self, nlp, gold_tuples):
self.nlp = nlp self.nlp = nlp
self.gold_tuples = gold_tuples self.gold_tuples = gold_tuples
self.nr_epoch = 0
def epochs(self, nr_epoch, augment_data=None, gold_preproc=False): def epochs(self, nr_epoch, augment_data=None, gold_preproc=False):
cached_golds = {} cached_golds = {}
def _epoch(indices): def _epoch(indices):
for i in indices: for i in tqdm.tqdm(indices):
raw_text, paragraph_tuples = self.gold_tuples[i] raw_text, paragraph_tuples = self.gold_tuples[i]
if gold_preproc: if gold_preproc:
raw_text = None raw_text = None
@ -39,11 +41,12 @@ class Trainer(object):
for itn in range(nr_epoch): for itn in range(nr_epoch):
random.shuffle(indices) random.shuffle(indices)
yield _epoch(indices) yield _epoch(indices)
self.nr_epoch += 1
def update(self, doc, gold): def update(self, doc, gold):
for process in self.nlp.pipeline: for process in self.nlp.pipeline:
if hasattr(process, 'update'): if hasattr(process, 'update'):
process.update(doc, gold) loss = process.update(doc, gold, itn=self.nr_epoch)
process(doc) process(doc)
return doc return doc