explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-02 09:56:39 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix size limits in train_textcat example

Browse Source
This commit is contained in:
Matthew Honnibal 2019-03-23 16:10:44 +01:00
parent b7c75049f7
commit 350785d8ce
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
examples/training/train_textcat.py
View File

@ -43,7 +43,11 @@ def main(model=None, output_dir=None, n_iter=20, n_texts=2000, init_tok2vec=None
# nlp.create_pipe works for built-ins that are registered with spaCy # nlp.create_pipe works for built-ins that are registered with spaCy
if "textcat" not in nlp.pipe_names: if "textcat" not in nlp.pipe_names:
textcat = nlp.create_pipe( textcat = nlp.create_pipe(
"textcat", config={"architecture": "simple_cnn", "exclusive_classes": True} "textcat",
config={
"exclusive_classes": True,
"architecture": "simple_cnn",
}
) )
nlp.add_pipe(textcat, last=True) nlp.add_pipe(textcat, last=True)
# otherwise, get it, so we can add labels to it # otherwise, get it, so we can add labels to it
@ -56,7 +60,9 @@ def main(model=None, output_dir=None, n_iter=20, n_texts=2000, init_tok2vec=None
# load the IMDB dataset # load the IMDB dataset
print("Loading IMDB data...") print("Loading IMDB data...")
(train_texts, train_cats), (dev_texts, dev_cats) = load_data(limit=n_texts) (train_texts, train_cats), (dev_texts, dev_cats) = load_data()
train_texts = train_texts[:n_texts]
train_cats = train_cats[:n_texts]
print( print(
"Using {} examples ({} training, {} evaluation)".format( "Using {} examples ({} training, {} evaluation)".format(
n_texts, len(train_texts), len(dev_texts) n_texts, len(train_texts), len(dev_texts)