def as_sequences(self, variable=None):
'''
Convert a Value to a sequence of NumPy arrays that have their masked
entries removed.
Returns:
If variable contains more dynamic axes than the batch axis, a list
of NumPy arrays (if dense) or a SciPy CSR array (if sparse) will be
returned. Otherwise, the arrays will be returned directly.
'''
if self.is_sparse:
if variable is None:
raise ValueError('cannot convert sparse value to sequences '
'without the corresponding variable')
network = _sparse_to_dense_network_cache(variable.shape, True,
self.device)
warnings.warn(
'converting Value object to CSR format might be slow')
# TODO: Add direct conversion, since creating an intermediate array might be slow
dense_data = network.eval(self, device=self.device)
return [sparse.csr_matrix(seq) for seq in dense_data]
else:
# Checking for mask without retrieving
has_mask = super(Value, self).mask() is not None
if has_mask:
if variable is None:
mask = self.mask
return [
seq[mask[idx] != cntk_py.MaskKind_Invalid]
for idx, seq in enumerate(self.data.asarray())
]
else:
value_sequences = self.unpack_variable_value(
variable, True, cpu())
return [seq.asarray() for seq in value_sequences[0]]
else:
# This might be costly, but we need to return a list for
# consistency.
arr = self.asarray()
if not arr.shape:
return [arr]
else:
return list(arr)
def asarray(variable, value):
'''
Converts a Value object to a sequence of NumPy arrays (if dense) or CSR arrays (if sparse).
'''
if value.is_sparse():
network = _sparse_to_dense_network_cache(variable.shape)
warnings.warn('converting Value object to CSR format might be very costly')
# TODO: Add direct conversion, since creating an intermediate array might be very slow
dense_data = network.eval(value, value.device())
array_to_return = [sparse.csr_matrix(seq) for seq in dense_data]
else:
array_to_return = Value.to_seq(value, variable)
return array_to_return
def as_sequences(self, variable=None):
'''
Convert a Value to a sequence of NumPy arrays that have their masked
entries removed.
Returns:
If variable contains more dynamic axes than the batch axis, a list
of NumPy arrays (if dense) or a SciPy CSR array (if sparse) will be
returned. Otherwise, the arrays will be returned directly.
'''
if self.is_sparse:
if variable is None:
raise ValueError('cannot convert sparse value to sequences '
'without the corresponding variable')
network = _sparse_to_dense_network_cache(variable.shape, True, self.device)
warnings.warn('converting Value object to CSR format might be slow')
# TODO: Add direct conversion, since creating an intermediate array might be slow
dense_data = network.eval(self, device=self.device)
return [sparse.csr_matrix(seq) for seq in dense_data]
else:
# Checking for mask without retrieving
has_mask = super(Value, self).mask() is not None
if has_mask:
if variable is None:
mask = self.mask
return [seq[mask[idx] != cntk_py.MaskKind_Invalid]
for idx, seq in enumerate(self.data.asarray())]
else:
value_sequences = self.unpack_variable_value(variable, True, cpu())
return [seq.asarray() for seq in value_sequences[0]]
else:
# This might be costly, but we need to return a list for
# consistency.
arr = self.asarray()
if not arr.shape:
return [arr]
else:
return list(arr)
def asarray(self):
'''
Converts the instance's data to a NumPy array.
'''
import cntk
result = None
if isinstance(self, cntk.Constant):
ndav = super(cntk.Constant, self).value()
is_sparse = ndav.is_sparse()
elif isinstance(self, cntk.Parameter):
ndav = super(cntk.Parameter, self).value()
is_sparse = ndav.is_sparse()
elif isinstance(self, (cntk.cntk_py.Constant, cntk.cntk_py.Parameter)):
ndav = self.value()
is_sparse = ndav.is_sparse()
elif isinstance(self, (cntk.cntk_py.NDArrayView, cntk.cntk_py.NDMask)):
ndav = self
if isinstance(self, cntk.NDArrayView):
is_sparse = ndav.is_sparse
elif isinstance(self, cntk.cntk_py.NDArrayView):
is_sparse = ndav.is_sparse()
else:
is_sparse = False
# Value and MinibatchData have a mask, which means that we need the
# corresponding Variable to do the proper conversion. For easy
# discoverability, we nevertheless add asarray() to those classes as
# well, but issue a warning.
elif isinstance(self, cntk.cntk_py.Value) or isinstance(self, cntk.cntk_py.MinibatchData):
if isinstance(self, cntk.cntk_py.MinibatchData):
value = self.data
else:
value = self
if isinstance(value, cntk.Value):
is_sparse = value.is_sparse
has_mask = super(cntk.Value, value).mask() is not None
ndav = value.data
else:
is_sparse = value.is_sparse()
has_mask = value.mask() is not None
ndav = value.data()
if has_mask:
warnings.warn('asarray() will ignore the mask information. '
'Please use as_sequences() to do the proper '
'conversion.')
if is_sparse:
from cntk.internal.sanitize import _sparse_to_dense_network_cache
device = ndav.device
if callable(device):
device = device()
network = _sparse_to_dense_network_cache(ndav.shape[1:], False,
device)
warnings.warn('converting Value object to CSR format might be slow')
dense_data = network.eval(self, device=device)
def to_csr(dense_data):
if len(dense_data.shape) > 2:
raise ValueError('Cannot convert a sparse NDArrayView or Value object '
'with shape %s of rank > 2 to a scipy.csr matrix.' % str(dense_data.shape))
return sparse.csr_matrix(dense_data)
if isinstance(dense_data, list):
result = [to_csr(d) for d in dense_data]
else:
result = to_csr(dense_data)
else:
result = ndav.to_ndarray()
return result
def asarray(self):
'''
Converts the instance's data to a NumPy array.
'''
import cntk
result = None
if isinstance(self, cntk.Constant):
ndav = super(cntk.Constant, self).value()
is_sparse = ndav.is_sparse()
elif isinstance(self, cntk.Parameter):
ndav = super(cntk.Parameter, self).value()
is_sparse = ndav.is_sparse()
elif isinstance(self, (cntk.cntk_py.Constant, cntk.cntk_py.Parameter)):
ndav = self.value()
is_sparse = ndav.is_sparse()
elif isinstance(self, (cntk.cntk_py.NDArrayView, cntk.cntk_py.NDMask)):
ndav = self
if isinstance(self, cntk.NDArrayView):
is_sparse = ndav.is_sparse
elif isinstance(self, cntk.cntk_py.NDArrayView):
is_sparse = ndav.is_sparse()
else:
is_sparse = False
# Value and MinibatchData have a mask, which means that we need the
# corresponding Variable to do the proper conversion. For easy
# discoverability, we nevertheless add asarray() to those classes as
# well, but issue a warning.
elif isinstance(self, cntk.cntk_py.Value) or isinstance(
self, cntk.cntk_py.MinibatchData):
if isinstance(self, cntk.cntk_py.MinibatchData):
value = self.data
else:
value = self
if isinstance(value, cntk.Value):
is_sparse = value.is_sparse
has_mask = super(cntk.Value, value).mask() is not None
ndav = value.data
else:
is_sparse = value.is_sparse()
has_mask = value.mask() is not None
ndav = value.data()
if has_mask:
warnings.warn('asarray() will ignore the mask information. '
'Please use as_sequences() to do the proper '
'conversion.')
if is_sparse:
from cntk.internal.sanitize import _sparse_to_dense_network_cache
device = ndav.device
if callable(device):
device = device()
network = _sparse_to_dense_network_cache(ndav.shape[1:], False,
device)
warnings.warn(
'converting Value object to CSR format might be slow')
dense_data = network.eval(self, device=device)
def to_csr(dense_data):
if len(dense_data.shape) > 2:
raise ValueError(
'Cannot convert a sparse NDArrayView or Value object '
'with shape %s of rank > 2 to a scipy.csr matrix.' %
str(dense_data.shape))
return sparse.csr_matrix(dense_data)
if isinstance(dense_data, list):
result = [to_csr(d) for d in dense_data]
else:
result = to_csr(dense_data)
else:
result = ndav.to_ndarray()
return result
