Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Tidy up [ci skip]

This commit is contained in:
Ines Montani 2020-10-01 10:41:19 +02:00
parent 381258b75b
commit 44160cd52f
2 changed files with 1 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/cli/train.py
View File

@ -1,15 +1,13 @@
from typing import Optional from typing import Optional
from pathlib import Path from pathlib import Path
from wasabi import msg from wasabi import msg
from thinc.api import Config
import typer import typer
import logging import logging
from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error
from ._util import import_code, setup_gpu from ._util import import_code, setup_gpu
from ..language import Language
from ..training.loop import train from ..training.loop import train
from ..training.initialize import init_nlp, must_reinitialize from ..training.initialize import init_nlp
from .. import util from .. import util

8
spacy/training/initialize.py
View File

@ -9,7 +9,6 @@ import gzip
import zipfile import zipfile
import tqdm import tqdm
from .loop import create_before_to_disk_callback
from ..lookups import Lookups from ..lookups import Lookups
from ..vectors import Vectors from ..vectors import Vectors
from ..errors import Errors from ..errors import Errors
@ -39,7 +38,6 @@ def init_nlp(config: Config, *, use_gpu: int = -1) -> "Language":
dot_names = [T["train_corpus"], T["dev_corpus"]] dot_names = [T["train_corpus"], T["dev_corpus"]]
train_corpus, dev_corpus = resolve_dot_names(config, dot_names) train_corpus, dev_corpus = resolve_dot_names(config, dot_names)
optimizer = T["optimizer"] optimizer = T["optimizer"]
before_to_disk = create_before_to_disk_callback(T["before_to_disk"])
# Components that shouldn't be updated during training # Components that shouldn't be updated during training
frozen_components = T["frozen_components"] frozen_components = T["frozen_components"]
# Sourced components that require resume_training # Sourced components that require resume_training
@ -55,15 +53,9 @@ def init_nlp(config: Config, *, use_gpu: int = -1) -> "Language":
# Verify the config after calling 'initialize' to ensure labels # Verify the config after calling 'initialize' to ensure labels
# are properly initialized # are properly initialized
verify_config(nlp) verify_config(nlp)
nlp = before_to_disk(nlp)
return nlp return nlp
def must_reinitialize(train_config: Config, init_config: Config) -> bool:
# TODO: do this better and more fine-grained
return train_config.interpolate().to_str() == init_config.interpolate().to_str()
def init_vocab( def init_vocab(
nlp: "Language", nlp: "Language",
*, *,