def generate_test_vectorss():
vss = vectorss()
vss.append(generate_test_vectors())
vss.append(generate_test_vectors())
vss.append(generate_test_vectors())
assert len(vss) == 3
return vss
segments.append(names)
names.clear()
# Now before we can pass these training sentences to the dlib tools we need to
# convert them into arrays of vectors as discussed above. We can use either a
# sparse or dense representation depending on our needs. In this example, we
# show how to do it both ways.
use_sparse_vects = False
if use_sparse_vects:
# Make an array of arrays of dlib.sparse_vector objects.
training_sequences = dlib.sparse_vectorss()
for s in sentences:
training_sequences.append(sentence_to_sparse_vectors(s))
else:
# Make an array of arrays of dlib.vector objects.
training_sequences = dlib.vectorss()
for s in sentences:
training_sequences.append(sentence_to_vectors(s))
# Now that we have a simple training set we can train a sequence segmenter.
# However, the sequence segmentation trainer has some optional parameters we can
# set. These parameters determine properties of the segmentation model we will
# learn. See the dlib documentation for the sequence_segmenter object for a
# full discussion of their meanings.
params = dlib.segmenter_params()
params.window_size = 3
params.use_high_order_features = True
params.use_BIO_model = True
# This is the common SVM C parameter. Larger values encourage the trainer to
# attempt to fit the data exactly but might overfit. In general, you determine
# this parameter by cross-validation.
segments.append(names)
names.clear()
# Now before we can pass these training sentences to the dlib tools we need to convert them
# into arrays of vectors as discussed above. We can use either a sparse or dense
# representation depending on our needs. In this example, we show how to do it both ways.
use_sparse_vects = False
if use_sparse_vects:
# Make an array of arrays of dlib.sparse_vector objects.
training_sequences = dlib.sparse_vectorss()
for s in sentences:
training_sequences.append(sentence_to_sparse_vectors(s))
else:
# Make an array of arrays of dlib.vector objects.
training_sequences = dlib.vectorss()
for s in sentences:
training_sequences.append(sentence_to_vectors(s))
# Now that we have a simple training set we can train a sequence segmenter. However, the
# sequence segmentation trainer has some optional parameters we can set. These parameters
# determine properties of the segmentation model we will learn. See the dlib documentation
# for the sequence_segmenter object for a full discussion of their meanings.
params = dlib.segmenter_params()
params.window_size = 3
params.use_high_order_features = True
params.use_BIO_model = True
# This is the common SVM C parameter. Larger values encourage the trainer to attempt to
# fit the data exactly but might overfit. In general, you determine this parameter by
def test_vectorss_extend():
vss = vectorss()
vss.extend([generate_test_vectors(), generate_test_vectors()])
assert len(vss) == 2
def test_vectorss_resize():
vss = vectorss()
vss.resize(100)
assert len(vss) == 100
for i in range(100):
assert len(vss[i]) == 0
