explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Offer option of padding-sensitive batching

Browse Source
This commit is contained in:
Matthw Honnibal 2020-07-09 14:50:20 +02:00
parent 3a7f275c02
commit 77af0a6bb4
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/cli/train.py
View File

@ -303,11 +303,19 @@ def create_train_batches(nlp, corpus, cfg):
)
epoch = 0
batch_strategy = cfg.get("batch_by", "sequences")
while True:
if len(train_examples) == 0:
raise ValueError(Errors.E988)
epoch += 1
if cfg.get("batch_by_words", True):
if batch_strategy == "padded":
batches = util.minibatch_by_padded_size(
train_examples,
size=cfg["batch_size"],
buffer=256,
discard_oversize=cfg["discard_oversize"],
)
elif batch_strategy == "words":
batches = util.minibatch_by_words(
train_examples,
size=cfg["batch_size"],