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

Dont randomize cuts in parser

This commit is contained in:
Matthw Honnibal 2020-07-06 17:51:25 +02:00
parent 709fc5e4ad
commit f25761e513
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/syntax/nn_parser.pyx
View File

@ -280,11 +280,12 @@ cdef class Parser:
[eg.predicted for eg in examples])
if self.cfg["update_with_oracle_cut_size"] >= 1:
# Chop sequences into lengths of this many transitions, to make the
# batch uniform length. We randomize this to overfit less.
# batch uniform length.
# We used to randomize this, but it's not clear that actually helps?
cut_size = self.cfg["update_with_oracle_cut_size"]
states, golds, max_steps = self._init_gold_batch(
examples,
max_length=numpy.random.choice(range(5, cut_size))
max_length=cut_size
)
else:
states, golds, _ = self.moves.init_gold_batch(examples)