def test_large_minibatch(tmpdir):
tmpfile = _write_data(tmpdir, MBDATA_DENSE_2)
mb_source = MinibatchSource(CTFDeserializer(
tmpfile,
StreamDefs(features=StreamDef(field='S0', shape=1),
labels=StreamDef(field='S1', shape=1))),
randomization_window_in_chunks=0)
features_si = mb_source.stream_info('features')
labels_si = mb_source.stream_info('labels')
mb = mb_source.next_minibatch(1000)
features = mb[features_si]
labels = mb[labels_si]
# Actually, the minibatch spans over multiple sweeps,
# not sure if this is an artificial situation, but
# maybe instead of a boolean flag we should indicate
# the largest sweep index the data was taken from.
assert features.end_of_sweep
assert labels.end_of_sweep
assert features.num_samples == 1000 - 1000 % 7
assert labels.num_samples == 5 * (1000 // 7)
assert mb[features_si].num_sequences == (1000 // 7)
assert mb[labels_si].num_sequences == (1000 // 7)
def test_large_minibatch(tmpdir):
tmpfile = _write_data(tmpdir, MBDATA_DENSE_2)
mb_source = MinibatchSource(CTFDeserializer(tmpfile, StreamDefs(
features = StreamDef(field='S0', shape=1),
labels = StreamDef(field='S1', shape=1))),
randomization_window_in_chunks=0)
features_si = mb_source.stream_info('features')
labels_si = mb_source.stream_info('labels')
mb = mb_source.next_minibatch(1000)
features = mb[features_si]
labels = mb[labels_si]
# Actually, the minibatch spans over multiple sweeps,
# not sure if this is an artificial situation, but
# maybe instead of a boolean flag we should indicate
# the largest sweep index the data was taken from.
assert features.end_of_sweep
assert labels.end_of_sweep
assert features.num_samples == 1000 - 1000 % 7
assert labels.num_samples == 5 * (1000 // 7)
assert mb[features_si].num_sequences == (1000 // 7)
assert mb[labels_si].num_sequences == (1000 // 7)
def test_minibatch(tmpdir):
mbdata = r'''0 |S0 0 |S1 0
0 |S0 1 |S1 1
0 |S0 2
0 |S0 3 |S1 3
1 |S0 4
1 |S0 5 |S1 1
1 |S0 6 |S1 2
'''
tmpfile = str(tmpdir/'mbtest.txt')
with open(tmpfile, 'w') as f:
f.write(mbdata)
from cntk.io import CTFDeserializer, MinibatchSource, StreamDef, StreamDefs
mb_source = MinibatchSource(CTFDeserializer(tmpfile, StreamDefs(
features = StreamDef(field='S0', shape=1),
labels = StreamDef(field='S1', shape=1))))
features_si = mb_source.stream_info('features')
labels_si = mb_source.stream_info('labels')
mb = mb_source.next_minibatch(1000)
assert mb[features_si].num_sequences == 2
assert mb[labels_si].num_sequences == 2
features = mb[features_si]
assert len(features.value) == 2
expected_features = \
[
[[0],[1],[2],[3]],
[[4],[5],[6]]
]
for res, exp in zip (features.value, expected_features):
assert np.allclose(res, exp)
assert np.allclose(features.mask,
[[2, 1, 1, 1],
[2, 1, 1, 0]])
labels = mb[labels_si]
assert len(labels.value) == 2
expected_labels = \
[
[[0],[1],[3]],
[[1],[2]]
]
for res, exp in zip (labels.value, expected_labels):
assert np.allclose(res, exp)
assert np.allclose(labels.mask,
[[2, 1, 1],
[2, 1, 0]])
def test_text_format(tmpdir):
tmpfile = _write_data(tmpdir, MBDATA_SPARSE)
input_dim = 1000
num_output_classes = 5
mb_source = MinibatchSource(CTFDeserializer(
tmpfile,
StreamDefs(features=StreamDef(field='x',
shape=input_dim,
is_sparse=True),
labels=StreamDef(field='y',
shape=num_output_classes,
is_sparse=False))),
randomize=False)
assert isinstance(mb_source, MinibatchSource)
features_si = mb_source.stream_info('features')
labels_si = mb_source.stream_info('labels')
mb = mb_source.next_minibatch(7)
features = mb[features_si]
# 2 samples, max seq len 4, 1000 dim
assert features.shape == (2, 4, input_dim)
assert features.end_of_sweep
assert features.num_sequences == 2
assert features.num_samples == 7
assert features.is_sparse
labels = mb[labels_si]
# 2 samples, max seq len 1, 5 dim
assert labels.shape == (2, 1, num_output_classes)
assert labels.end_of_sweep
assert labels.num_sequences == 2
assert labels.num_samples == 2
assert not labels.is_sparse
label_data = labels.asarray()
assert np.allclose(
label_data, np.asarray([[[1., 0., 0., 0., 0.]], [[0., 1., 0., 0.,
0.]]]))
mb = mb_source.next_minibatch(1)
features = mb[features_si]
labels = mb[labels_si]
assert not features.end_of_sweep
assert not labels.end_of_sweep
assert features.num_samples < 7
assert labels.num_samples == 1
def test_text_format(tmpdir):
from cntk.io import CTFDeserializer, MinibatchSource, StreamDef, StreamDefs
mbdata = r'''0 |x 560:1 |y 1 0 0 0 0
0 |x 0:1
0 |x 0:1
1 |x 560:1 |y 0 1 0 0 0
1 |x 0:1
1 |x 0:1
1 |x 424:1
'''
tmpfile = str(tmpdir/'mbdata.txt')
with open(tmpfile, 'w') as f:
f.write(mbdata)
input_dim = 1000
num_output_classes = 5
mb_source = MinibatchSource(CTFDeserializer(tmpfile, StreamDefs(
features = StreamDef(field='x', shape=input_dim, is_sparse=True),
labels = StreamDef(field='y', shape=num_output_classes, is_sparse=False)
)))
assert isinstance(mb_source, MinibatchSource)
features_si = mb_source.stream_info('features')
labels_si = mb_source.stream_info('labels')
mb = mb_source.next_minibatch(7)
features = mb[features_si]
# 2 samples, max seq len 4, 1000 dim
assert features.shape == (2, 4, input_dim)
assert features.is_sparse
# TODO features is sparse and cannot be accessed right now:
# *** RuntimeError: DataBuffer/WritableDataBuffer methods can only be called for NDArrayiew objects with dense storage format
# 2 samples, max seq len 4, 1000 dim
#assert features.data().shape().dimensions() == (2, 4, input_dim)
#assert features.data().is_sparse()
labels = mb[labels_si]
# 2 samples, max seq len 1, 5 dim
assert labels.shape == (2, 1, num_output_classes)
assert not labels.is_sparse
label_data = np.asarray(labels)
assert np.allclose(label_data,
np.asarray([
[[ 1., 0., 0., 0., 0.]],
[[ 0., 1., 0., 0., 0.]]
]))
def test_text_format(tmpdir):
tmpfile = _write_data(tmpdir, MBDATA_SPARSE)
input_dim = 1000
num_output_classes = 5
mb_source = MinibatchSource(CTFDeserializer(tmpfile, StreamDefs(
features=StreamDef(field='x', shape=input_dim, is_sparse=True),
labels=StreamDef(field='y', shape=num_output_classes, is_sparse=False)
)), randomize=False)
assert isinstance(mb_source, MinibatchSource)
features_si = mb_source.stream_info('features')
labels_si = mb_source.stream_info('labels')
mb = mb_source.next_minibatch(7)
features = mb[features_si]
# 2 samples, max seq len 4, 1000 dim
assert features.shape == (2, 4, input_dim)
assert features.end_of_sweep
assert features.num_sequences == 2
assert features.num_samples == 7
assert features.is_sparse
labels = mb[labels_si]
# 2 samples, max seq len 1, 5 dim
assert labels.shape == (2, 1, num_output_classes)
assert labels.end_of_sweep
assert labels.num_sequences == 2
assert labels.num_samples == 2
assert not labels.is_sparse
label_data = labels.asarray()
assert np.allclose(label_data,
np.asarray([
[[1., 0., 0., 0., 0.]],
[[0., 1., 0., 0., 0.]]
]))
mb = mb_source.next_minibatch(1)
features = mb[features_si]
labels = mb[labels_si]
assert not features.end_of_sweep
assert not labels.end_of_sweep
assert features.num_samples < 7
assert labels.num_samples == 1
def test_MinibatchData_and_Value_as_input(tmpdir):
mbdata = r'''0 |S0 100'''
tmpfile = str(tmpdir / 'mbtest.txt')
with open(tmpfile, 'w') as f:
f.write(mbdata)
defs = StreamDefs(f1=StreamDef(field='S0', shape=1))
mb_source = MinibatchSource(CTFDeserializer(tmpfile, defs),
randomize=False)
f1_si = mb_source.stream_info('f1')
mb = mb_source.next_minibatch(1)
f1 = input(shape=(1, ), needs_gradient=True, name='f')
res = f1 * 2
assert res.eval({f1: mb[f1_si]}) == [[200]]
# Test MinibatchData
assert res.eval(mb[f1_si]) == [[200]]
# Test Value
assert res.eval(mb[f1_si].data) == [[200]]
# Test NumPy (converted back from MinibatchData)
assert res.eval(mb[f1_si].asarray()) == [[200]]
# Test Value
assert res.eval(mb[f1_si].data) == [[200]]
def test_MinibatchData_and_Value_as_input(tmpdir):
mbdata = r'''0 |S0 100'''
tmpfile = str(tmpdir/'mbtest.txt')
with open(tmpfile, 'w') as f:
f.write(mbdata)
defs = StreamDefs(f1 = StreamDef(field='S0', shape=1))
mb_source = MinibatchSource(CTFDeserializer(tmpfile, defs),
randomize=False)
f1_si = mb_source.stream_info('f1')
mb = mb_source.next_minibatch(1)
f1 = input_variable(shape=(1,),
needs_gradient=True,
name='f')
res = f1 * 2
assert res.eval({f1: mb[f1_si]}) == [[200]]
# Test MinibatchData
assert res.eval(mb[f1_si]) == [[200]]
# Test Value
assert res.eval(mb[f1_si].data) == [[200]]
# Test NumPy (converted back from MinibatchData)
assert res.eval(mb[f1_si].value) == [[200]]
# Test Value
assert res.eval(mb[f1_si].data) == [[200]]
def test_full_sweep_minibatch(tmpdir):
tmpfile = _write_data(tmpdir, MBDATA_DENSE_1)
mb_source = MinibatchSource(CTFDeserializer(tmpfile, StreamDefs(
features = StreamDef(field='S0', shape=1),
labels = StreamDef(field='S1', shape=1))),
randomization_window_in_chunks=0, max_sweeps=1)
features_si = mb_source.stream_info('features')
labels_si = mb_source.stream_info('labels')
mb = mb_source.next_minibatch(1000)
assert mb[features_si].num_sequences == 2
assert mb[labels_si].num_sequences == 2
features = mb[features_si]
assert features.end_of_sweep
assert len(features.as_sequences()) == 2
expected_features = \
[
[[0], [1], [2], [3]],
[[4], [5], [6]]
]
for res, exp in zip(features.as_sequences(), expected_features):
assert np.allclose(res, exp)
assert np.allclose(features.data.mask,
[[2, 1, 1, 1],
[2, 1, 1, 0]])
labels = mb[labels_si]
assert labels.end_of_sweep
assert len(labels.as_sequences()) == 2
expected_labels = \
[
[[0],[1],[3]],
[[1],[2]]
]
for res, exp in zip(labels.as_sequences(), expected_labels):
assert np.allclose(res, exp)
assert np.allclose(labels.data.mask,
[[2, 1, 1],
[2, 1, 0]])
def test_full_sweep_minibatch(tmpdir):
tmpfile = _write_data(tmpdir, MBDATA_DENSE_1)
mb_source = MinibatchSource(CTFDeserializer(tmpfile, StreamDefs(
features = StreamDef(field='S0', shape=1),
labels = StreamDef(field='S1', shape=1))),
randomization_window_in_chunks=0, max_sweeps=1)
features_si = mb_source.stream_info('features')
labels_si = mb_source.stream_info('labels')
mb = mb_source.next_minibatch(1000)
assert mb[features_si].num_sequences == 2
assert mb[labels_si].num_sequences == 2
features = mb[features_si]
assert features.end_of_sweep
assert len(features.as_sequences()) == 2
expected_features = \
[
[[0], [1], [2], [3]],
[[4], [5], [6]]
]
for res, exp in zip(features.as_sequences(), expected_features):
assert np.allclose(res, exp)
assert np.allclose(features.data.mask,
[[2, 1, 1, 1],
[2, 1, 1, 0]])
labels = mb[labels_si]
assert labels.end_of_sweep
assert len(labels.as_sequences()) == 2
expected_labels = \
[
[[0],[1],[3]],
[[1],[2]]
]
for res, exp in zip(labels.as_sequences(), expected_labels):
assert np.allclose(res, exp)
assert np.allclose(labels.data.mask,
[[2, 1, 1],
[2, 1, 0]])