def sanitize_batch(batch, data_type=None, dev=None):
"""
Convert to Value with `data_type`. If the samples in `batch` have different
sequence lengths, pad them to max sequence length and create a mask.
Args:
batch (list of NumPy arrays): input
Returns:
converted batch
"""
from ..cntk_py import Value
if isinstance(batch, Value):
return batch
num_seq = len(batch)
try:
seq_lens = [len(seq) for seq in batch]
except:
import ipdb;ipdb.set_trace()
use_mask = len(set(seq_lens))!=1
if use_mask:
# If not all sequences are of the same length, we have to pad them to
# the same length and create a mask over the original data.
from cntk.cntk_py import NDMask
mask = NDMask((max(seq_lens), num_seq), dev)
for idx, seq_len in enumerate(seq_lens):
mask.mask_section((seq_len, idx), (cntk_py.InferredDimension, 1))
# Then we pad the batch to rectangular shape
if isinstance(batch, list):
if len(batch)==0:
raise ValueError('batch is empty')
batch = pad_to_dense(batch)
# If it still is not an NumPy array, try brute force...
if not isinstance(batch, np.ndarray):
batch = np.asarray(batch, dtype=data_type)
'''
if is_tensor(values) or is_tensor_list(values):
values = np.asarray(values)
if dynamic_axis:
cntk_shape = values[0].shape[1:]
else:
cntk_shape = values[0].shape
if len(cntk_shape) == 0:
raise ValueError('values should be an array of input samples')
'''
ndav = create_NDArrayView_from_NumPy(batch, dev)
if use_mask:
value = Value(ndav, mask)
else:
value = Value(ndav)
return value
def sanitize_batch(batch, data_type=None, dev=None):
"""
Convert to Value with `data_type`. If the samples in `batch` have different
sequence lengths, pad them to max sequence length and create a mask.
Args:
batch (list of NumPy arrays): input
Returns:
converted batch
"""
from ..cntk_py import Value
if isinstance(batch, Value):
return batch
num_seq = len(batch)
try:
seq_lens = [len(seq) for seq in batch]
except:
import ipdb
ipdb.set_trace()
use_mask = len(set(seq_lens)) != 1
if use_mask:
# If not all sequences are of the same length, we have to pad them to
# the same length and create a mask over the original data.
from cntk.cntk_py import NDMask
mask = NDMask((max(seq_lens), num_seq), dev)
for idx, seq_len in enumerate(seq_lens):
mask.mask_section((seq_len, idx), (cntk_py.InferredDimension, 1))
# Then we pad the batch to rectangular shape
if isinstance(batch, list):
if len(batch) == 0:
raise ValueError('batch is empty')
batch = pad_to_dense(batch)
# If it still is not an NumPy array, try brute force...
if not isinstance(batch, np.ndarray):
batch = np.asarray(batch, dtype=data_type)
'''
if is_tensor(values) or is_tensor_list(values):
values = np.asarray(values)
if dynamic_axis:
cntk_shape = values[0].shape[1:]
else:
cntk_shape = values[0].shape
if len(cntk_shape) == 0:
raise ValueError('values should be an array of input samples')
'''
ndav = create_NDArrayView_from_NumPy(batch, dev)
if use_mask:
value = Value(ndav, mask)
else:
value = Value(ndav)
return value
def sanitize_batch(var, batch, seq_starts=None, data_type=None, device=None):
'''
Convert to :class:`cntk.cntk_py.Value` with ``data_type``. If the samples in ``batch`` have
different sequence lengths, pad them to max sequence length and create a
mask.
Args:
var (`:class:cntk.ops.variables.Variable`): variable node for which the ``batch`` is
meant
batch (`list` of NumPy arrays): input
seq_starts (`list` of `bool` or `None`): if `None`, every sequence is
treated as a new sequence. Otherwise, it is interpreted as a list of
Booleans that tell whether a sequence is a new sequence (`True`) or a
continuation of the previous one (`False`)
Returns:
`:class:cntk.cntk_py.Value`: converted batch
'''
from ..cntk_py import Value
if isinstance(batch, Value):
return batch
use_mask = False
if isinstance(batch, np.ndarray):
if batch.dtype == np.int:
batch = batch.astype(np.float32)
elif batch.dtype not in (np.float32, np.float64):
raise ValueError('only float32 and float64 are supported')
elif isinstance(batch, list):
if is_tensor_list(batch):
use_mask = len(var.dynamic_axes) > 1
if device is None:
device = cntk_py.DeviceDescriptor.use_default_device()
if not use_mask and seq_starts is not None:
raise ValueError('specification of individual sequence begins does not'
' make sense when not using the sequence axis')
# Use the mask, if we have additional dynamic axes besides the batch axis
if use_mask:
seq_lens = [len(seq) for seq in batch]
try:
num_seq = len(batch)
except TypeError:
raise ValueError('expected an object of type Value or a NumPy ' +
'array and not "%s"' % type(batch))
from cntk.cntk_py import NDMask
mask = NDMask((max(seq_lens), num_seq), device)
for idx, seq_len in enumerate(seq_lens):
if seq_starts is None:
mask.mark_sequence_begin((0, idx))
elif seq_starts[idx]:
mask.mark_sequence_begin((0, idx))
mask.invalidate_section((seq_len, idx),
(cntk_py.InferredDimension, 1))
# Then we pad the batch to rectangular shape
if isinstance(batch, list):
if len(batch) == 0:
raise ValueError('batch is empty')
batch = pad_to_dense(batch)
# If it still is not an NumPy array, try brute force...
if not isinstance(batch, np.ndarray):
if data_type is None:
data_type = get_data_type(var)
batch = np.asarray(batch, dtype=data_type)
# Maybe a NumPy dtype was given, but with lower accuracy than float32, then
# convert it to float32
if np.issubdtype(batch.dtype, int):
batch = batch.astype(np.float32)
if len(cntk_shape) == 0:
raise ValueError('values should be an array of input samples')
ndav = create_NDArrayView_from_NumPy(batch, device)
if use_mask:
value = Value(ndav, mask)
else:
value = Value(ndav)
return value
def sanitize_batch(var, batch, seq_starts=None, data_type=None, device=None):
'''
Convert to :class:`cntk.cntk_py.Value` with ``data_type``. If the samples in ``batch`` have
different sequence lengths, pad them to max sequence length and create a
mask.
Args:
var (:class:`cntk.ops.variables.Variable`): variable node for which the ``batch`` is
meant
batch (`list` of NumPy arrays): input
seq_starts (`list` of `bool` or `None`): if `None`, every sequence is
treated as a new sequence. Otherwise, it is interpreted as a list of
Booleans that tell whether a sequence is a new sequence (`True`) or a
continuation of the previous one (`False`)
Returns:
:class:`cntk.cntk_py.Value`: converted batch
'''
from ..cntk_py import Value
if isinstance(batch, Value):
return batch
use_mask = False
if isinstance(batch, np.ndarray):
if batch.dtype == np.int:
batch = batch.astype(np.float32)
elif batch.dtype not in (np.float32, np.float64):
raise ValueError('only float32 and float64 are supported')
elif isinstance(batch, list):
if is_tensor_list(batch):
use_mask = len(var.dynamic_axes) > 1
if device is None:
device = use_default_device()
if not use_mask and seq_starts is not None:
raise ValueError('specification of individual sequence begins does not'
' make sense when not using the sequence axis')
# Use the mask, if we have additional dynamic axes besides the batch axis
if use_mask:
seq_lens = [len(seq) for seq in batch]
try:
num_seq = len(batch)
except TypeError:
raise ValueError('expected an object of type Value or a NumPy ' +
'array and not "%s"' % type(batch))
from cntk.cntk_py import NDMask
mask = NDMask((max(seq_lens), num_seq), device)
for idx, seq_len in enumerate(seq_lens):
if seq_starts is None:
mask.mark_sequence_begin((0, idx))
elif seq_starts[idx]:
mask.mark_sequence_begin((0, idx))
mask.invalidate_section((seq_len, idx),
(cntk_py.InferredDimension, 1))
# Then we pad the batch to rectangular shape
if isinstance(batch, list):
if len(batch) == 0:
raise ValueError('batch is empty')
batch = pad_to_dense(batch)
# If it still is not an NumPy array, try brute force...
if not isinstance(batch, np.ndarray):
if data_type is None:
data_type = get_data_type(var)
batch = np.asarray(batch, dtype=data_type)
# Maybe a NumPy dtype was given, but with lower accuracy than float32, then
# convert it to float32
if np.issubdtype(batch.dtype, int):
batch = batch.astype(np.float32)
if len(cntk_shape) == 0:
raise ValueError('values should be an array of input samples')
ndav = create_NDArrayView_from_NumPy(batch, device)
if use_mask:
value = Value(ndav, mask)
else:
value = Value(ndav)
return value