def main(batch_size=3):
import random
from recnn_util import load_data
train_trees, dev_trees, test_trees, token2id = load_data(
"data/stanford_sentiment_treebank.pkl")
sys.stderr.write("Data load done")
batch_number = len(train_trees) / batch_size
x = T.imatrix('x')
y = T.ivector('y')
model = RNTN(
x,
y,
vocab_size=len(token2id),
embed_dim=10,
label_n=5,
)
sys.stderr.write("Model compilation done\n")
training_iter = 0
validation_frequency = 10
print "start training.."
while True:
# shuffle data
random.shuffle(train_trees)
# for each mini-batch in
for i in xrange(batch_number):
training_iter += 1
batch_trees = train_trees[i * batch_size:(i + 1) * batch_size]
batch_nodes = collect_nodes(batch_trees)
x, y = build_input(batch_nodes, token2id)
# train the model()
model.update_embedding(x)
model.train(x, y)
print "At iter %d" % (training_iter)
if training_iter % validation_frequency == 0:
classifier = NumpyRNTN.load_from_theano_model(model, token2id)
def accuracy(trees):
prediction = np.array(
[classifier.predict_top_node(tree) for tree in trees])
correct = np.array([tree[0] for tree in trees])
return np.mean(prediction == correct)
print "At iter %d, train accuracy %.2f%%, dev accuracy %.2f%%" % (
training_iter, accuracy(train_trees) * 100,
accuracy(dev_trees) * 100)
def main(batch_size = 3):
import random
from recnn_util import load_data
train_trees, dev_trees, test_trees, token2id = load_data("data/stanford_sentiment_treebank.pkl")
sys.stderr.write("Data load done")
batch_number = len(train_trees) / batch_size
x = T.imatrix('x')
y = T.ivector('y')
model = RNTN(
x, y,
vocab_size = len(token2id),
embed_dim = 10,
label_n = 5,
)
sys.stderr.write("Model compilation done\n")
training_iter = 0
validation_frequency = 10
print "start training.."
while True:
# shuffle data
random.shuffle(train_trees)
# for each mini-batch in
for i in xrange(batch_number):
training_iter += 1
batch_trees = train_trees[i*batch_size:(i+1)*batch_size]
batch_nodes = collect_nodes(batch_trees)
x,y = build_input(batch_nodes, token2id)
# train the model()
model.update_embedding(x)
model.train(x, y)
print "At iter %d" %(training_iter)
if training_iter % validation_frequency == 0:
classifier = NumpyRNTN.load_from_theano_model(model, token2id)
def accuracy(trees):
prediction = np.array([classifier.predict_top_node(tree) for tree in trees])
correct = np.array([tree[0] for tree in trees])
return np.mean(prediction == correct)
print "At iter %d, train accuracy %.2f%%, dev accuracy %.2f%%" %(training_iter,
accuracy(train_trees) * 100,
accuracy(dev_trees) * 100)
vocab_size = 6
embed_dim = 3
label_n = 5
word2id = {
'I': 0,
'love': 1,
'you': 2,
'<UNK>': 5,
}
x = T.imatrix('x')
y = T.ivector('y')
th_model = TheanoRNTN(x, y, vocab_size, embed_dim, label_n)
np_model = NumpyRNTN.load_from_theano_model(
th_model, word2id) # (embedding = th_model.embedding.get_value(),
# rntn_layer = RNTNLayer(th_model.rntn_layer.V.get_value(), th_model.rntn_layer.W.get_value()),
# logreg_layer = LogisticRegression(th_model.logreg_layer.W.get_value(), th_model.logreg_layer.b.get_value()),
# word2id = word2id)
x_input = np.asarray([[4, 2, 5], [3, 1, 4]], dtype=np.int32)
tree_input = (5, "love", (3, (3, "you"), (3, "bro")))
actual = np_model.get_node_vector(tree_input)
th_model.update_embedding(x_input)
expected = th_model.embedding.get_value()[3]
assert_matrix_eq(actual, expected, "node vector")
embed_dim = 3
label_n = 5
word2id = {
'I': 0,
'love': 1,
'you':2,
'<UNK>': 5,
}
x = T.imatrix('x')
y = T.ivector('y')
th_model = TheanoRNTN(x, y, vocab_size, embed_dim, label_n)
np_model = NumpyRNTN.load_from_theano_model(th_model, word2id)# (embedding = th_model.embedding.get_value(),
# rntn_layer = RNTNLayer(th_model.rntn_layer.V.get_value(), th_model.rntn_layer.W.get_value()),
# logreg_layer = LogisticRegression(th_model.logreg_layer.W.get_value(), th_model.logreg_layer.b.get_value()),
# word2id = word2id)
x_input = np.asarray([[4, 2, 5],
[3, 1, 4]],
dtype=np.int32)
tree_input = (5, "love", (3, (3, "you"), (3, "bro")))
actual = np_model.get_node_vector(tree_input)
th_model.update_embedding(x_input)
expected = th_model.embedding.get_value()[3]
