return dataset
# Split into training and test data.
dataset = get_dataset()
split = int(0.66 * len(dataset.data))
train_data, test_data = dataset.data[:split], dataset.data[split:]
train_target, test_target = dataset.target[:split], dataset.target[split:]
# Compute graph.
_, length, image_size = train_data.shape
num_classes = train_target.shape[2]
data = tf.placeholder(tf.float32, [None, length, image_size])
target = tf.placeholder(tf.float32, [None, length, num_classes])
model = BidirectionalSequenceLabellingModel(data, target, params)
batches = batched(train_data, train_target, params.batch_size)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for index, batch in enumerate(batches):
batch_data = batch[0]
batch_target = batch[1]
epoch = batch[2]
if epoch >= params.epochs:
break
feed = {data: batch_data, target: batch_target}
error, _ = sess.run([model.error, model.optimize], feed)
if index % params.epoch_size == 0:
print('{}: {:3.2f}%'.format(index, 100 * error))
test_feed = {data: test_data, target: test_target}
return dataset
# Split into training and test data.
dataset = get_dataset()
split = int(0.66 * len(dataset.data))
train_data, test_data = dataset.data[:split], dataset.data[split:]
train_target, test_target = dataset.target[:split], dataset.target[split:]
# Compute graph.
_, length, image_size = train_data.shape
num_classes = train_target.shape[2]
data = tf.placeholder(tf.float32, [None, length, image_size])
target = tf.placeholder(tf.float32, [None, length, num_classes])
model = BidirectionalSequenceLabellingModel(data, target, params)
batches = batched(train_data, train_target, params.batch_size)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
for index, batch in enumerate(batches):
batch_data = batch[0]
batch_target = batch[1]
epoch = batch[2]
if epoch >= params.epochs:
break
feed = {data: batch_data, target: batch_target}
error, _ = sess.run([model.error, model.optimize], feed)
print("{}: {:3.6f}%".format(index + 1, 100 * error))
test_feed = {data: test_data, target: test_target}
test_error, _ = sess.run([model.error, model.optimize], test_feed)
contrastive_examples=100,
learning_rate=0.5,
momentum=0.5,
batch_size=1000,
)
data = tf.placeholder(tf.int32, [None])
target = tf.placeholder(tf.int32, [None])
model = EmbeddingModel(data, target, params)
corpus = Wikipedia(
'https://dumps.wikimedia.org/enwiki/20160501/'
'enwiki-20160501-pages-meta-current1.xml-p000000010p000030303.bz2',
WIKI_DOWNLOAD_DIR, params.vocabulary_size)
examples = skipgrams(corpus, params.max_context)
batches = batched(examples, params.batch_size)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
average = collections.deque(maxlen=100)
for index, batch in enumerate(batches):
feed_dict = {data: batch[0], target: batch[1]}
cost, _ = sess.run([model.cost, model.optimize], feed_dict)
average.append(cost)
print('{}: {:5.1f}'.format(index + 1, sum(average) / len(average)))
if index > 100000:
break
embeddings = sess.run(model.embeddings)
np.save(WIKI_DOWNLOAD_DIR + '/embeddings.npy', embeddings)
learning_rate=0.5,
momentum=0.5,
batch_size=1000,
)
data = tf.placeholder(tf.int32, [None])
target = tf.placeholder(tf.int32, [None])
model = EmbeddingModel(data, target, params)
corpus = Wikipedia(
'https://dumps.wikimedia.org/enwiki/20160501/'
'enwiki-20160501-pages-meta-current1.xml-p000000010p000030303.bz2',
WIKI_DOWNLOAD_DIR,
params.vocabulary_size)
examples = skipgrams(corpus, params.max_context)
batches = batched(examples, params.batch_size)
sess = tf.Session()
sess.run(tf.initialize_all_variables())
average = collections.deque(maxlen=100)
for index, batch in enumerate(batches):
feed_dict = {data: batch[0], target: batch[1]}
cost, _ = sess.run([model.cost, model.optimize], feed_dict)
average.append(cost)
print('{}: {:5.1f}'.format(index + 1, sum(average) / len(average)))
if index > 100000:
break
embeddings = sess.run(model.embeddings)
np.save(WIKI_DOWNLOAD_DIR + '/embeddings.npy', embeddings)
