explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 01:16:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Tweaks to train script

Browse Source
This commit is contained in:
Matthew Honnibal 2017-05-25 17:15:24 -05:00
parent 3a6e59cc53
commit df8015f05d
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/cli/train.py
View File

@ -57,9 +57,9 @@ def train(_, lang, output_dir, train_data, dev_data, n_iter=20, n_sents=0,
# starts high and decays sharply, to force the optimizer to explore. # starts high and decays sharply, to force the optimizer to explore.
# Batch size starts at 1 and grows, so that we make updates quickly # Batch size starts at 1 and grows, so that we make updates quickly
# at the beginning of training. # at the beginning of training.
dropout_rates = util.decaying(util.env_opt('dropout_from', 0.0), dropout_rates = util.decaying(util.env_opt('dropout_from', 0.5),
util.env_opt('dropout_to', 0.0), util.env_opt('dropout_to', 0.2),
util.env_opt('dropout_decay', 0.0)) util.env_opt('dropout_decay', 1e-4))
batch_sizes = util.compounding(util.env_opt('batch_from', 1), batch_sizes = util.compounding(util.env_opt('batch_from', 1),
util.env_opt('batch_to', 64), util.env_opt('batch_to', 64),
util.env_opt('batch_compound', 1.001)) util.env_opt('batch_compound', 1.001))
@ -72,7 +72,7 @@ def train(_, lang, output_dir, train_data, dev_data, n_iter=20, n_sents=0,
print("Itn.\tDep. Loss\tUAS\tNER P.\tNER R.\tNER F.\tTag %\tToken %") print("Itn.\tDep. Loss\tUAS\tNER P.\tNER R.\tNER F.\tTag %\tToken %")
for i in range(n_iter): for i in range(n_iter):
with tqdm.tqdm(total=corpus.count_train()) as pbar: with tqdm.tqdm(total=corpus.count_train(), leave=False) as pbar:
train_docs = corpus.train_docs(nlp, projectivize=True, train_docs = corpus.train_docs(nlp, projectivize=True,
gold_preproc=False, shuffle=i) gold_preproc=False, shuffle=i)
losses = {} losses = {}