explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Load vectors in 'spacy train'

Browse Source
This commit is contained in:
Matthew Honnibal 2020-07-28 22:00:24 +02:00
parent 7852a68a75
commit 2aff3c4b5a
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/cli/train.py
View File

@ -80,16 +80,20 @@ def train(
msg.info("Using CPU")
msg.info(f"Loading config and nlp from: {config_path}")
config = Config().from_disk(config_path)
if config.get("training", {}).get("seed") is not None:
fix_random_seed(config["training"]["seed"])
with show_validation_error():
nlp, config = util.load_model_from_config(config, overrides=config_overrides)
if config["training"]["base_model"]:
base_nlp = util.load_model(config["training"]["base_model"])
# TODO: do something to check base_nlp against regular nlp described in config?
nlp = base_nlp
# If everything matches it will look something like:
# base_nlp = util.load_model(config["training"]["base_model"])
# nlp = base_nlp
raise NotImplementedError("base_model not supported yet.")
if config["training"]["vectors"] is not None:
util.load_vectors_into_model(nlp, config["training"]["vectors"])
verify_config(nlp)
raw_text, tag_map, morph_rules, weights_data = load_from_paths(config)
if config["training"]["seed"] is not None:
fix_random_seed(config["training"]["seed"])
if config["training"]["use_pytorch_for_gpu_memory"]:
# It feels kind of weird to not have a default for this.
use_pytorch_for_gpu_memory()