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

Corretions for model test example 

The sentences of test data in sentence entailment example should be generated with integers limited to vocab_size.
This commit is contained in:
akYoung 2017-05-03 22:41:23 +08:00 committed by GitHub
parent 6e1fad92a1
commit c158cdb1da
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/keras_parikh_entailment/keras_decomposable_attention.py
View File

@ -256,9 +256,9 @@ def test_fit_model():
settings = {'lr': 0.001, 'dropout': 0.2, 'gru_encode':True}
model = build_model(vectors, shape, settings)
train_X = _generate_X(20, shape[0], vectors.shape[1])
train_X = _generate_X(20, shape[0], vectors.shape[0])
train_Y = _generate_Y(20, shape[2])
dev_X = _generate_X(15, shape[0], vectors.shape[1])
dev_X = _generate_X(15, shape[0], vectors.shape[0])
dev_Y = _generate_Y(15, shape[2])
model.fit(train_X, train_Y, validation_data=(dev_X, dev_Y), nb_epoch=5,