def create_mb_source(image_height, image_width, num_channels, map_file):
transforms = [ImageDeserializer.scale(width=image_width, height=image_height, channels=num_channels, interpolations='linear')]
image_source = ImageDeserializer(map_file)
image_source.ignore_labels()
image_source.map_features('features', transforms)
return MinibatchSource(image_source, randomize=False)
def create_image_mb_source(map_file, is_training, total_number_of_samples):
if not os.path.exists(map_file):
raise RuntimeError("File '%s' does not exist." %map_file)
# transformation pipeline for the features has jitter/crop only when training
transforms = []
if is_training:
transforms += [
xforms.crop(crop_type='randomside', side_ratio=0.4375:0.875, jitter_type='uniratio') # train uses jitter
]
else:
transforms += [
xforms.crop(crop_type='center', side_ratio=0.5833333) # test has no jitter
]
transforms += [
xforms.scale(width=image_width, height=image_height, channels=num_channels, interpolations='linear'),
]
# deserializer
return MinibatchSource(
ImageDeserializer(map_file, StreamDefs(
features = StreamDef(field='image', transforms=transforms), # first column in map file is referred to as 'image'
labels = StreamDef(field='label', shape=num_classes))), # and second as 'label'
randomize = is_training,
epoch_size=total_number_of_samples,
multithreaded_deserializer = True)
def create_mb_source(image_height, image_width, num_channels, map_file, mean_file, is_training):
if not os.path.exists(map_file):
raise RuntimeError("File '%s' does not exist." % (map_file))
# transformation pipeline for the features has jitter/crop only when training
transforms = []
if is_training:
transforms += [
xforms.crop(crop_type='randomside', side_ratio=0.875, jitter_type='uniratio') # train uses jitter
]
else:
transforms += [
xforms.crop(crop_type='center', side_ratio=0.875) # test has no jitter
]
transforms += [
xforms.scale(width=image_width, height=image_height, channels=num_channels, interpolations='linear'),
]
if mean_file != '':
transforms += [
xforms.mean(mean_file),
]
# deserializer
return MinibatchSource(
ImageDeserializer(map_file, StreamDefs(
features = StreamDef(field='image', transforms=transforms) # first column in map file is referred to as 'image'
)),
randomize = is_training,
multithreaded_deserializer = True,
max_sweeps = 1)
def create_reader(path,
vocab_dim,
entity_dim,
randomize,
rand_size=DEFAULT_RANDOMIZATION_WINDOW,
size=INFINITELY_REPEAT):
"""
Create data reader for the model
Args:
path: The data path
vocab_dim: The dimention of the vocabulary
entity_dim: The dimention of entities
randomize: Where to shuffle the data before feed into the trainer
"""
return MinibatchSource(CTFDeserializer(
path,
StreamDefs(context=StreamDef(field='C',
shape=vocab_dim,
is_sparse=True),
query=StreamDef(field='Q', shape=vocab_dim, is_sparse=True),
entities=StreamDef(field='E', shape=1, is_sparse=False),
label=StreamDef(field='L', shape=1, is_sparse=False),
entity_ids=StreamDef(field='EID',
shape=entity_dim,
is_sparse=True))),
randomize=randomize)
def create_video_mb_source(map_files, num_channels, image_height, image_width,
num_classes):
transforms = [
xforms.crop(crop_type='center', crop_size=224),
xforms.scale(width=image_width,
height=image_height,
channels=num_channels,
interpolations='linear')
]
map_files = sorted(map_files,
key=lambda x: int(x.split('Map_')[1].split('.')[0]))
print(map_files)
# Create multiple image sources
sources = []
for i, map_file in enumerate(map_files):
streams = {
"feature" + str(i): StreamDef(field='image',
transforms=transforms),
"label" + str(i): StreamDef(field='label', shape=num_classes)
}
sources.append(ImageDeserializer(map_file, StreamDefs(**streams)))
return MinibatchSource(sources, max_sweeps=1, randomize=False)
def create_mb_source(img_height, img_width, img_channels, n_classes, n_rois, data_path, data_set):
rois_dim = 4 * n_rois
label_dim = n_classes * n_rois
path = os.path.normpath(os.path.join(abs_path, data_path))
if data_set == 'test':
map_file = os.path.join(path, test_map_filename)
else:
map_file = os.path.join(path, train_map_filename)
roi_file = os.path.join(path, data_set + rois_filename_postfix)
label_file = os.path.join(path, data_set + roilabels_filename_postfix)
if not os.path.exists(map_file) or not os.path.exists(roi_file) or not os.path.exists(label_file):
raise RuntimeError("File '%s', '%s' or '%s' does not exist. "
"Please run install_fastrcnn.py from Examples/Image/Detection/FastRCNN to fetch them" %
(map_file, roi_file, label_file))
# read images
image_source = ImageDeserializer(map_file)
image_source.ignore_labels()
image_source.map_features(features_stream_name,
[ImageDeserializer.scale(width=img_width, height=img_height, channels=img_channels,
scale_mode="pad", pad_value=114, interpolations='linear')])
# read rois and labels
roi_source = CTFDeserializer(roi_file)
roi_source.map_input(roi_stream_name, dim=rois_dim, format="dense")
label_source = CTFDeserializer(label_file)
label_source.map_input(label_stream_name, dim=label_dim, format="dense")
# define a composite reader
return MinibatchSource([image_source, roi_source, label_source], epoch_size=sys.maxsize, randomize=data_set == "train")
def create_mb_source(data_set, img_height, img_width, n_classes, n_rois, data_path, randomize):
# set paths
map_file = join(data_path, data_set + '.txt')
roi_file = join(data_path, data_set + '.rois.txt')
label_file = join(data_path, data_set + '.roilabels.txt')
if not os.path.exists(map_file) or not os.path.exists(roi_file) or not os.path.exists(label_file):
raise RuntimeError("File '%s', '%s' or '%s' does not exist. " % (map_file, roi_file, label_file))
# read images
nrImages = len(readTable(map_file))
transforms = [scale(width=img_width, height=img_height, channels=3,
scale_mode="pad", pad_value=114, interpolations='linear')]
image_source = ImageDeserializer(map_file, StreamDefs(features = StreamDef(field='image', transforms=transforms)))
# read rois and labels
rois_dim = 4 * n_rois
label_dim = n_classes * n_rois
roi_source = CTFDeserializer(roi_file, StreamDefs(
rois = StreamDef(field='rois', shape=rois_dim, is_sparse=False)))
label_source = CTFDeserializer(label_file, StreamDefs(
roiLabels = StreamDef(field='roiLabels', shape=label_dim, is_sparse=False)))
# define a composite reader
mb = MinibatchSource([image_source, roi_source, label_source], epoch_size=sys.maxsize, randomize=randomize)
return (mb, nrImages)
def create_reader(map_file, train, dimensions, classes,
total_number_of_samples):
print(
f"Reading map file: {map_file} with number of samples {total_number_of_samples}"
)
# transformation pipeline for the features has jitter/crop only when training
transforms = []
# finalize_network uses data augmentation (translation only)
if train:
transforms += [
xforms.crop(crop_type='randomside',
area_ratio=(0.08, 1.0),
aspect_ratio=(0.75, 1.3333),
jitter_type='uniratio'),
xforms.color(brightness_radius=0.4,
contrast_radius=0.4,
saturation_radius=0.4)
]
transforms += [
xforms.scale(width=dimensions['width'],
height=dimensions['height'],
channels=dimensions['depth'],
interpolations='linear')
]
source = MinibatchSource(ImageDeserializer(
map_file,
StreamDefs(features=StreamDef(field='image', transforms=transforms),
labels=StreamDef(field='label', shape=len(classes)))),
randomize=train,
max_samples=total_number_of_samples,
multithreaded_deserializer=True)
return source
def create_reader(map_file, mean_file, train):
if not os.path.exists(map_file) or not os.path.exists(mean_file):
raise RuntimeError(
"File '%s' or '%s' does not exist. Please run install_cifar10.py from DataSets/CIFAR-10 to fetch them"
% (map_file, mean_file))
# transformation pipeline for the features has jitter/crop only when training
transforms = []
if train:
transforms += [
ImageDeserializer.crop(crop_type='randomside',
side_ratio=0.8,
jitter_type='uniratio') # train uses jitter
]
transforms += [
ImageDeserializer.scale(width=image_width,
height=image_height,
channels=num_channels,
interpolations='linear'),
ImageDeserializer.mean(mean_file)
]
# deserializer
return MinibatchSource(
ImageDeserializer(
map_file,
StreamDefs(
features=StreamDef(
field='image', transforms=transforms
), # first column in map file is referred to as 'image'
labels=StreamDef(field='label',
shape=num_classes)))) # and second as 'label'
def create_reader(map_file,
mean_file,
train,
image_height=64,
image_width=64,
num_channels=3,
num_classes=32):
# transformation pipeline for the features has jitter/crop only when training
# https://docs.microsoft.com/en-us/python/api/cntk.io.transforms?view=cntk-py-2.2
trs = []
if train:
trs += [
transforms.crop(crop_type='randomside',
side_ratio=0,
jitter_type='none') # Horizontal flip enabled
]
trs += [
transforms.scale(width=image_width,
height=image_height,
channels=num_channels,
interpolations='linear'),
transforms.mean(mean_file)
]
# deserializer
image_source = ImageDeserializer(
map_file,
StreamDefs(
features=StreamDef(
field='image', transforms=trs
), # first column in map file is referred to as 'image'
labels=StreamDef(field='label',
shape=num_classes) # and second as 'label'
))
return MinibatchSource(image_source)
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_create_two_image_deserializers(tmpdir):
mbdata = r'''filename 0
filename2 0
'''
map_file = str(tmpdir / 'mbdata.txt')
with open(map_file, 'w') as f:
f.write(mbdata)
image_width = 100
image_height = 200
num_channels = 3
transforms = [
xforms.crop(crop_type='randomside',
side_ratio=0.5,
jitter_type='uniratio'),
xforms.scale(width=image_width,
height=image_height,
channels=num_channels,
interpolations='linear')
]
image1 = ImageDeserializer(
map_file,
StreamDefs(f1=StreamDef(field='image', transforms=transforms)))
image2 = ImageDeserializer(
map_file,
StreamDefs(f2=StreamDef(field='image', transforms=transforms)))
mb_source = MinibatchSource([image1, image2])
assert isinstance(mb_source, MinibatchSource)
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_multiple_mlf_files():
os.chdir(data_path)
feature_dim = 33
num_classes = 132
context = 2
test_mlf_path = "../../../../Tests/EndToEndTests/Speech/Data/glob_00001.mlf"
features_file = "glob_0000.scp"
label_files = ["glob_0000.mlf", test_mlf_path]
label_mapping_file = "state.list"
fd = HTKFeatureDeserializer(
StreamDefs(amazing_features=StreamDef(
shape=feature_dim, context=(context, context), scp=features_file)))
ld = HTKMLFDeserializer(
label_mapping_file,
StreamDefs(
awesome_labels=StreamDef(shape=num_classes, mlf=label_files)))
# Make sure we can read at least one minibatch.
mbsource = MinibatchSource([fd, ld])
mbsource.next_minibatch(1)
os.chdir(abs_path)
def create_reader(map_file, mean_file, train, distributed_communicator=None):
if not os.path.exists(map_file) or not os.path.exists(mean_file):
cifar_py3 = "" if sys.version_info.major < 3 else "_py3"
raise RuntimeError(
"File '%s' or '%s' does not exist. Please run CifarDownload%s.py and CifarConverter%s.py from CIFAR-10 to fetch them"
% (map_file, mean_file, cifar_py3, cifar_py3))
# transformation pipeline for the features has jitter/crop only when training
transforms = []
if train:
transforms += [
ImageDeserializer.crop(crop_type='Random',
ratio=0.8,
jitter_type='uniRatio') # train uses jitter
]
transforms += [
ImageDeserializer.scale(width=image_width,
height=image_height,
channels=num_channels,
interpolations='linear'),
ImageDeserializer.mean(mean_file)
]
# deserializer
return MinibatchSource(
ImageDeserializer(
map_file,
StreamDefs(
features=StreamDef(
field='image', transforms=transforms
), # first column in map file is referred to as 'image'
labels=StreamDef(field='label',
shape=num_classes))), # and second as 'label'
distributed_communicator=distributed_communicator)
def test_base64_image_deserializer(tmpdir):
import io, base64, uuid
from PIL import Image
images, b64_images = [], []
np.random.seed(1)
for i in range(10):
data = np.random.randint(0, 2**8, (5, 7, 3))
image = Image.fromarray(data.astype('uint8'), "RGB")
buf = io.BytesIO()
image.save(buf, format='PNG')
assert image.width == 7 and image.height == 5
b64_images.append(base64.b64encode(buf.getvalue()))
images.append(np.array(image))
image_data = str(tmpdir / 'mbdata1.txt')
seq_ids = []
uid = uuid.uuid1().int >> 64
with open(image_data, 'wb') as f:
for i, data in enumerate(b64_images):
seq_id = uid ^ i
seq_id = str(seq_id).encode('ascii')
seq_ids.append(seq_id)
line = seq_id + b'\t'
label = str(i).encode('ascii')
line += label + b'\t' + data + b'\n'
f.write(line)
ctf_data = str(tmpdir / 'mbdata2.txt')
with open(ctf_data, 'wb') as f:
for i, sid in enumerate(seq_ids):
line = sid + b'\t' + b'|index ' + str(i).encode('ascii') + b'\n'
f.write(line)
transforms = [xforms.scale(width=7, height=5, channels=3)]
b64_deserializer = Base64ImageDeserializer(
image_data,
StreamDefs(images=StreamDef(field='image', transforms=transforms),
labels=StreamDef(field='label', shape=10)))
ctf_deserializer = CTFDeserializer(
ctf_data, StreamDefs(index=StreamDef(field='index', shape=1)))
mb_source = MinibatchSource([ctf_deserializer, b64_deserializer])
assert isinstance(mb_source, MinibatchSource)
for j in range(100):
mb = mb_source.next_minibatch(10)
index_stream = mb_source.streams['index']
index = mb[index_stream].asarray().flatten()
image_stream = mb_source.streams['images']
results = mb[image_stream].asarray()
for i in range(10):
# original images are RBG, openCV produces BGR images,
# reverse the last dimension of the original images
bgrImage = images[int(index[i])][:, :, ::-1]
assert (bgrImage == results[i][0]).all()
def create_reader(map_file, mean_file, train):
# transformation pipeline for the features has jitter/crop only when training
trs = []
# if train:
# transforms += [
# ImageDeserializer.crop(crop_type='Random', ratio=0.8, jitter_type='uniRatio') # train uses jitter
# ]
trs += [
transforms.scale(width=image_width,
height=image_height,
channels=num_channels,
interpolations='linear'),
transforms.mean(mean_file)
]
# deserializer
return MinibatchSource(
ImageDeserializer(
map_file,
StreamDefs(
features=StreamDef(
field='image', transforms=trs
), # first column in map file is referred to as 'image'
labels=StreamDef(field='label',
shape=num_classes) # and second as 'label'
)))
def test_eval_sparse_dense(tmpdir, device_id):
from cntk import Axis
from cntk.io import MinibatchSource, CTFDeserializer, StreamDef, StreamDefs
from cntk.ops import input, times
input_vocab_dim = label_vocab_dim = 69
ctf_data = '''\
0 |S0 3:1 |# <s> |S1 3:1 |# <s>
0 |S0 4:1 |# A |S1 32:1 |# ~AH
0 |S0 5:1 |# B |S1 36:1 |# ~B
0 |S0 4:1 |# A |S1 31:1 |# ~AE
0 |S0 7:1 |# D |S1 38:1 |# ~D
0 |S0 12:1 |# I |S1 47:1 |# ~IY
0 |S0 1:1 |# </s> |S1 1:1 |# </s>
2 |S0 60:1 |# <s> |S1 3:1 |# <s>
2 |S0 61:1 |# A |S1 32:1 |# ~AH
'''
ctf_file = str(tmpdir / '2seqtest.txt')
with open(ctf_file, 'w') as f:
f.write(ctf_data)
mbs = MinibatchSource(CTFDeserializer(
ctf_file,
StreamDefs(features=StreamDef(field='S0',
shape=input_vocab_dim,
is_sparse=True),
labels=StreamDef(field='S1',
shape=label_vocab_dim,
is_sparse=True))),
randomize=False,
epoch_size=2)
raw_input = sequence.input(shape=input_vocab_dim,
sequence_axis=Axis('inputAxis'),
name='raw_input',
is_sparse=True)
mb_valid = mbs.next_minibatch(minibatch_size_in_samples=100,
input_map={raw_input: mbs.streams.features},
device=cntk_device(device_id))
z = times(raw_input, np.eye(input_vocab_dim))
e_reader = z.eval(mb_valid, device=cntk_device(device_id))
# CSR with the raw_input encoding in ctf_data
one_hot_data = [[3, 4, 5, 4, 7, 12, 1], [60, 61]]
data = [
csr(np.eye(input_vocab_dim, dtype=np.float32)[d]) for d in one_hot_data
]
e_csr = z.eval({raw_input: data}, device=cntk_device(device_id))
assert np.all([np.allclose(a, b) for a, b in zip(e_reader, e_csr)])
# One-hot with the raw_input encoding in ctf_data
data = Value.one_hot(one_hot_data,
num_classes=input_vocab_dim,
device=cntk_device(device_id))
e_hot = z.eval({raw_input: data}, device=cntk_device(device_id))
assert np.all([np.allclose(a, b) for a, b in zip(e_reader, e_hot)])
def create_mb_source(map_file, image_width, image_height, num_channels, num_classes, randomize=True):
transforms = []
transforms += [xforms.crop(crop_type='randomside', side_ratio=0.8)]
transforms += [xforms.scale(width=image_width, height=image_height, channels=num_channels, interpolations='linear')]
return MinibatchSource(ImageDeserializer(map_file, StreamDefs(
features =StreamDef(field='image', transforms=transforms),
labels =StreamDef(field='label', shape=num_classes))),
randomize=randomize)
def create_reader(path, is_training, input_dim, num_label_classes):
"""
reads CNTK formatted file with 'labels' and 'features'
"""
return MinibatchSource(CTFDeserializer(path, StreamDefs(
labels = StreamDef(field='labels', shape=num_label_classes),
features = StreamDef(field='features', shape=input_dim)
)), randomize = is_training, max_sweeps = INFINITELY_REPEAT if is_training else 1)
def create_reader(path, randomize, input_vocab_dim, label_vocab_dim, size=INFINITELY_REPEAT):
if not os.path.exists(path):
raise RuntimeError("File '%s' does not exist." % (path))
return MinibatchSource(CTFDeserializer(path, StreamDefs(
features = StreamDef(field='S0', shape=input_vocab_dim, is_sparse=True),
labels = StreamDef(field='S1', shape=label_vocab_dim, is_sparse=True)
)), randomize=randomize, max_samples = size)
def create_reader_raw(path, is_training, input_dim, num_label_classes):
"""
Reads in the unstardized values.
"""
return MinibatchSource(CTFDeserializer(path, StreamDefs(
labels = StreamDef(field='rawlabels', shape=num_label_classes),
features = StreamDef(field='rawfeatures', shape=input_dim)
)), randomize = is_training, max_sweeps = INFINITELY_REPEAT if is_training else 1)
def create_reader(path, is_training, input_dim, label_dim):
return MinibatchSource(
CTFDeserializer(
path,
StreamDefs(features=StreamDef(field='features', shape=input_dim),
labels=StreamDef(field='labels', shape=label_dim))),
randomize=is_training,
epoch_size=INFINITELY_REPEAT if is_training else FULL_DATA_SWEEP)
def test_htk_deserializers():
mbsize = 640
epoch_size = 1000 * mbsize
lr = [0.001]
feature_dim = 33
num_classes = 132
context = 2
os.chdir(data_path)
features_file = "glob_0000.scp"
labels_file = "glob_0000.mlf"
label_mapping_file = "state.list"
fd = HTKFeatureDeserializer(
StreamDefs(amazing_features=StreamDef(
shape=feature_dim, context=(context, context), scp=features_file)))
ld = HTKMLFDeserializer(
label_mapping_file,
StreamDefs(
awesome_labels=StreamDef(shape=num_classes, mlf=labels_file)))
reader = MinibatchSource([fd, ld])
features = C.input_variable(((2 * context + 1) * feature_dim))
labels = C.input_variable((num_classes))
model = Sequential(
[For(range(3), lambda: Recurrence(LSTM(256))),
Dense(num_classes)])
z = model(features)
ce = C.cross_entropy_with_softmax(z, labels)
errs = C.classification_error(z, labels)
learner = C.adam_sgd(z.parameters,
lr=C.learning_rate_schedule(lr, C.UnitType.sample,
epoch_size),
momentum=C.momentum_as_time_constant_schedule(1000),
low_memory=True,
gradient_clipping_threshold_per_sample=15,
gradient_clipping_with_truncation=True)
trainer = C.Trainer(z, (ce, errs), learner)
input_map = {
features: reader.streams.amazing_features,
labels: reader.streams.awesome_labels
}
pp = C.ProgressPrinter(freq=0)
# just run and verify it doesn't crash
for i in range(3):
mb_data = reader.next_minibatch(mbsize, input_map=input_map)
trainer.train_minibatch(mb_data)
pp.update_with_trainer(trainer, with_metric=True)
assert True
os.chdir(abs_path)
def test_index_caching(tmpdir):
pytest.skip("test_index_caching is disabled")
import os, time, glob, uuid
MB = 1 << 20
data = MBDATA_DENSE_1
while(len(data) < 64 * MB):
data += data
timeWithoutCache, timeWithCache = 0, 0
cpu=C.device.cpu()
streams = stream_defs[0]
for _ in range(3):
tmpfile = _write_data(tmpdir, data, str(uuid.uuid4()))
cache_files = glob.glob(str(tmpdir + '/*.cache'))
for cache_file in cache_files:
os.remove(cache_file)
config = CTFDeserializer(tmpfile, streams)
config['cacheIndex'] = C.cntk_py.DictionaryValue(True)
start = time.time()
MinibatchSource(config, randomize=False).next_minibatch(1, device=cpu)
end = time.time()
timeWithoutCache += (end - start)
time.sleep(5)
cache_files = glob.glob(str(tmpdir + '/*.cache'))
assert len(cache_files) == 1
start = time.time()
MinibatchSource(config, randomize=False).next_minibatch(1, device=cpu)
end = time.time()
os.remove(tmpfile)
timeWithCache += (end - start)
assert timeWithCache < timeWithoutCache
def compare_cbf_and_ctf(num_mbs, mb_size, randomize):
ctf = MinibatchSource(CTFDeserializer(tmpfile, streams),
randomize=randomize)
cbf = MinibatchSource(CBFDeserializer(tmpfile + '.bin', streams),
randomize=randomize)
ctf_stream_names = sorted([x.m_name for x in ctf.stream_infos()])
cbf_stream_names = sorted([x.m_name for x in cbf.stream_infos()])
assert (ctf_stream_names == cbf_stream_names)
for _ in range(num_mbs):
ctf_mb = ctf.next_minibatch(mb_size, device=device)
cbf_mb = cbf.next_minibatch(mb_size, device=device)
for name in cbf_stream_names:
ctf_data = ctf_mb[ctf[name]]
cbf_data = cbf_mb[cbf[name]]
assert ctf_data.num_samples == cbf_data.num_samples
assert ctf_data.num_sequences == cbf_data.num_sequences
assert ctf_data.shape == cbf_data.shape
assert ctf_data.end_of_sweep == cbf_data.end_of_sweep
assert ctf_data.is_sparse == cbf_data.is_sparse
assert ctf_data.data.masked_count(
) == cbf_data.data.masked_count()
# XXX:
# assert(ctf_data.asarray() == cbf_data.asarray()).all()
# not using asarray because for sparse values it fails with
# some strange exception "sum of the rank of the mask and Variable
#rank does not equal the Value's rank".
assert C.cntk_py.are_equal(ctf_data.data.data,
cbf_data.data.data)
if (ctf_data.data.masked_count() > 0):
assert (ctf_data.data.mask == cbf_data.data.mask).all()
# XXX: if mask_count is zero, mb_data.data.mask fails with
# "AttributeError: 'Value' object has no attribute 'mask'"!
# XXX: without invoking erase, next_minibatch will fail with:
# "Resize: Cannot resize the matrix because it is a view."
ctf_data.data.erase()
cbf_data.data.erase()
def test_one_sweep(tmpdir):
ctf = create_ctf_deserializer(tmpdir)
sources = [MinibatchSource(ctf, max_sweeps=1),
MinibatchSource(ctf, max_samples=FULL_DATA_SWEEP),
MinibatchSource(ctf, max_sweeps=1, max_samples=INFINITELY_REPEAT),
MinibatchSource(ctf, max_samples=FULL_DATA_SWEEP, max_sweeps=INFINITELY_REPEAT)]
for source in sources:
input_map = {'features': source['features']}
mb = source.next_minibatch(100, input_map)
assert 'features' in mb
assert mb['features'].num_samples == 4
assert mb['features'].end_of_sweep
mb = source.next_minibatch(100, input_map)
assert not mb
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 create_reader(path, is_training, input_dim, output_dim):
return MinibatchSource(CTFDeserializer(
path,
StreamDefs(features=StreamDef(field='attribs',
shape=input_dim,
is_sparse=False),
labels=StreamDef(field='species',
shape=output_dim,
is_sparse=False))),
randomize=is_training,
max_sweeps=INFINITELY_REPEAT if is_training else 1)
def create_reader(path, is_training):
return MinibatchSource(CTFDeserializer(
path,
StreamDefs(features=StreamDef(field='S0',
shape=input_vocab_dim,
is_sparse=True),
labels=StreamDef(field='S1',
shape=label_vocab_dim,
is_sparse=True))),
randomize=is_training,
max_sweeps=INFINITELY_REPEAT if is_training else 1)
