explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-26 01:04:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Increase length limit for pretrain

Browse Source
This commit is contained in:
Matthew Honnibal 2018-11-30 20:58:18 +00:00
parent 1b240f2119
commit 6bd1cc57ee
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/cli/pretrain.py
View File

@ -78,7 +78,7 @@ def make_update(model, docs, optimizer, drop=0.):
return loss return loss
def make_docs(nlp, batch): def make_docs(nlp, batch, min_length=1, max_length=500):
docs = [] docs = []
for record in batch: for record in batch:
text = record["text"] text = record["text"]
@ -91,7 +91,7 @@ def make_docs(nlp, batch):
heads = numpy.asarray(heads, dtype="uint64") heads = numpy.asarray(heads, dtype="uint64")
heads = heads.reshape((len(doc), 1)) heads = heads.reshape((len(doc), 1))
doc = doc.from_array([HEAD], heads) doc = doc.from_array([HEAD], heads)
if len(doc) >= 1 and len(doc) < 200: if len(doc) >= min_length and len(doc) < max_length:
docs.append(doc) docs.append(doc)
return docs return docs