def _to_config_description(self):
if self.reader is None:
if not self.unmapped_nodes:
# No inputs in the graph
return ''
# We have found only inputs that were directly initialized.
# In this case, we need to serialize them into one file.
from .context import get_context
from .utils import get_temp_filename
filename = get_temp_filename(get_context().directory)
if len(self.node_map) > 0:
raise ValueError(
'you cannot have inputs initialized with ' +
'NumPy arrays together with inputs that are ' +
' initialized with a custom reader')
self._serialize_unmapped_nodes(filename)
# All the data we got, was through NumPy. In this case, we assume
# that all the required randomization has happened already.
r = CNTKTextFormatReader(filename, randomize=None)
return r._to_config_description(self)
else:
return self.reader._to_config_description(self)
def _to_config_description(self):
if self.reader is None:
if not self.unmapped_nodes:
# No inputs in the graph
return ''
# We have found only inputs that were directly initialized.
# In this case, we need to serialize them into one file.
from .context import get_context
from .utils import get_temp_filename
filename = get_temp_filename(get_context().directory)
if len(self.node_map) > 0:
raise ValueError('you cannot have inputs initialized with '+
'NumPy arrays together with inputs that are ' +
' initialized with a custom reader')
self._serialize_unmapped_nodes(filename)
# All the data we got, was through NumPy. In this case, we assume
# that all the required randomization has happened already.
r = CNTKTextFormatReader(filename, randomize=None)
return r._to_config_description(self)
else:
return self.reader._to_config_description(self)
def _get_input_node(list_of_tensors, has_sequence_dimension, **kw):
'''
:param list_of_tensors: list of tensors potentially having sequences of
different lengths.
'''
# FIXME We need to better manage the context. How can we get hold
# of the overall context without having to always pass it
# explicitly?
from cntk.context import get_context
import tempfile
# We have to use NamedTemporaryFile and close it, because the obvious first
# choice, mkstemp(), would later fail in cntk.exe because the file would
# still be locked.
tf = tempfile.NamedTemporaryFile(prefix='_input_', suffix='.txt',
dir=get_context().directory, delete=False)
tf.close()
if 'alias' in kw:
alias = kw['alias']
del kw['alias'] # don't confuse with constructor's parameters
if not alias:
# TODO make sure we don't have clashes
alias = '_I_%i' % np.random.randint(1000)
shapes = set()
with open(tf.name, 'w') as f:
for idx,tensor in enumerate(list_of_tensors):
if isinstance(tensor, list):
tensor = np.asarray(tensor)
if has_sequence_dimension:
# collecting the shapes ignoring the sequence dimension
shapes.add(tensor.shape[1:])
else:
shapes.add(tensor.shape)
f.write(_tensor_to_text_format(idx, alias, tensor,
has_sequence_dimension) + '\n')
# ignoring the sequence dimension, all shapes should be equal
if len(shapes)!=1:
raise ValueError('except for the sequence dimensions all shapes ' +
'should be the same - instead we have: %s'%(", ".join(str(s) for s in shapes)))
# shapes now contains only one shape, which has the sequence dimension
# removed.
value_shape = shapes.pop()
cntk_shape = value_shape if value_shape else (1,)
node = cntk1_ops.Input(cntk_shape, **kw)
node.reader = CNTKTextFormatReader(tf.name, alias)
return node
def _get_constant_node(value, **kw):
'''
This function creates a node that represents `value` as a constant tensor
in the graph.
To be as generic as possible, we
- flatten the data
- initialize a ParameterTensor operator with it
- ensure that the graph does not backprob to it.
- Finally we to reshape it.
'''
# FIXME We need to better manage the context. How can we get hold
# of the overall context without having to always pass it
# explicitly?
from cntk.context import get_context
import tempfile
# We have to use NamedTemporaryFile and close it, because when using the
# obvious first choice, mkstemp(), would later fail in cntk.exe because the
# file would still be locked.
# TODO make it same filename as alias
tf = tempfile.NamedTemporaryFile(prefix='_param_',
suffix='.txt',
dir=get_context().directory,
delete=False)
tf.close()
if isinstance(value, list) or np.isscalar(value):
value = np.asarray(value)
if sparse.issparse(value):
raise ValueError('only dense data is supported')
with open(tf.name, 'w') as f:
value.ravel().tofile(f, sep='\n')
from cntk.reader import CNTKTextFormatReader
cntk_shape = numpy_to_cntk_shape(value.shape)
dims = np.multiply.reduce(cntk_shape)
# TODO switch to ConstantTensor once it is in the core.bs file
node = cntk1_ops.ParameterTensor(dims=dims,
learningRateMultiplier=0.0,
init='fromFile',
initFromFilePath=tf.name,
**kw)
if len(cntk_shape) > 1:
node = cntk1_ops.NewReshape(node, dims=cntk_shape)
return node
def _get_constant_node(value, **kw):
"""
This function creates a node that represents `value` as a constant tensor
in the graph.
To be as generic as possible, we
- flatten the data
- initialize a LearnableParameter operator with it
- ensure that the graph does not backprob to it.
- Finally we to reshape it.
"""
# FIXME We need to better manage the context. How can we get hold
# of the overall context without having to always pass it
# explicitly?
from cntk.context import get_context
import tempfile
# We have to use NamedTemporaryFile and close it, because when using the
# obvious first choice, mkstemp(), would later fail in cntk.exe because the
# file would still be locked.
# TODO make it same filename as alias
tf = tempfile.NamedTemporaryFile(prefix="_param_", suffix=".txt", dir=get_context().directory, delete=False)
tf.close()
if isinstance(value, list):
value = np.asarray(value)
if len(value.shape) == 1:
# 1D list: interpret as one scalar per sample
value = value[:, np.newaxis]
if sparse.issparse(value):
raise ValueError("only dense data is supported")
with open(tf.name, "w") as f:
# TODO value.ravel() ?
np.ndarray.flatten(value).tofile(f, sep="\n")
size = np.multiply.reduce(value.shape[:])
# The var_name specified by the user should be set to the operator that
# is finally returned, which is the shape node.
var_name = kw.pop("var_name", None)
from cntk.reader import CNTKTextFormatReader
param_node = cntk1_ops.LearnableParameter(
size, 1, learningRateMultiplier=0.0, init="fromFile", initFromFilePath=tf.name, **kw
)
reshape_node = cntk1_ops.NewReshape(param_node, dims=value.shape, var_name=var_name)
return reshape_node
def eval(node):
"""
It evaluates a node that has taken a numpy array as input. Note that sequences
are not supported yet by this method
Examples:
Plus with two matrices
>>> print (cntk.eval(cntk.ops.plus([[-30.,40.], [1.,2.]], [[-30.,40.], [1.,2.]])))
# [array([[[-60., 80.], [2., 4.]]])]
Times with broadcast of a scalar over a matrix
>>> print (cntk.eval(cntk.ops.element_times([[-30.,40.], [1.,2.]], 5)))
# [array([[[-150., 200.], [5., 10.]]])]
Args:
node (:class:`cntk.graph.ComputationNode`): the node to evaluate
Returns:
NumPy array containing the result
"""
from cntk.context import get_context
from cntk.ops import input_numpy, constant
from cntk.graph import ComputationNode
# call a helper method to get a context
ctx = get_context()
first = True
# The params are passed as arryas, e.g. plus([1,2], [3,4]), and we need to
# wrap them with input and parameter nodes.
if node.params:
for p in node.params:
if p in node.inputs:
val = getattr(node, p)
if not isinstance(val, ComputationNode):
# One param needs to be an Input() node. This will being fixed in
# CNTK soon, so that we can remove this workaround and evaluate a
# network with no inputs.
if first:
if not isinstance(val, list):
# inputs have the outmost dimension for sequences
val = [val]
ir = input_numpy([val], alias=p, name=p)
setattr(node, p, ir)
first = False
else:
setattr(node, p, constant(getattr(node, p), name=p))
else:
if val.op_name == 'CNTK2.Input' and first:
first = False
return ctx.eval(node)
def eval(node):
"""
It evaluates a node that has taken a numpy array as input. Note that sequences
are not supported yet by this method
Examples:
Plus with two matrices
>>> print (cntk.eval(cntk.ops.plus([[-30.,40.], [1.,2.]], [[-30.,40.], [1.,2.]])))
# [array([[[-60., 80.], [2., 4.]]])]
Times with broadcast of a scalar over a matrix
>>> print (cntk.eval(cntk.ops.element_times([[-30.,40.], [1.,2.]], 5)))
# [array([[[-150., 200.], [5., 10.]]])]
Args:
node (:class:`cntk.graph.ComputationNode`): the node to evaluate
Returns:
NumPy array containing the result
"""
from cntk.context import get_context
from cntk.ops import input_numpy, constant
from cntk.graph import ComputationNode
# call a helper method to get a context
ctx = get_context()
first = True
# The params are passed as arryas, e.g. plus([1,2], [3,4]), and we need to
# wrap them with input and parameter nodes.
if node.params:
for p in node.params:
if p in node.inputs:
val = getattr(node, p)
if not isinstance(val, ComputationNode):
# One param needs to be an Input() node. This will being fixed in
# CNTK soon, so that we can remove this workaround and evaluate a
# network with no inputs.
if first:
if not isinstance(val, list):
# inputs have the outmost dimension for sequences
val = [val]
ir = input_numpy([val], alias=p, name=p)
setattr(node, p, ir)
first = False
else:
setattr(node, p, constant(getattr(node, p), name=p))
else:
if val.op_name == 'CNTK2.Input' and first:
first = False
return ctx.eval(node)
def _get_constant_node(value, **kw):
'''
This function creates a node that represents `value` as a constant tensor
in the graph.
To be as generic as possible, we
- flatten the data
- initialize a ParameterTensor operator with it
- ensure that the graph does not backprob to it.
- Finally we to reshape it.
'''
# FIXME We need to better manage the context. How can we get hold
# of the overall context without having to always pass it
# explicitly?
from cntk.context import get_context
import tempfile
# We have to use NamedTemporaryFile and close it, because when using the
# obvious first choice, mkstemp(), would later fail in cntk.exe because the
# file would still be locked.
# TODO make it same filename as alias
tf = tempfile.NamedTemporaryFile(
prefix='_param_', suffix='.txt', dir=get_context().directory, delete=False)
tf.close()
if isinstance(value, list) or np.isscalar(value):
value = np.asarray(value)
if sparse.issparse(value):
raise ValueError('only dense data is supported')
with open(tf.name, 'w') as f:
value.ravel().tofile(f, sep='\n')
from cntk.reader import CNTKTextFormatReader
cntk_shape = numpy_to_cntk_shape(value.shape)
dims = np.multiply.reduce(cntk_shape)
# TODO switch to ConstantTensor once it is in the core.bs file
node = cntk1_ops.ParameterTensor(
dims=dims,
learningRateMultiplier=0.0,
init='fromFile',
initFromFilePath=tf.name,
**kw)
if len(cntk_shape) > 1:
node = cntk1_ops.NewReshape(node, dims=cntk_shape)
return node
def eval(node):
"""
It evaluates a node that has taken a numpy array as input. Note that sequences
are not supported yet by this method
Examples:
Plus with two matrices
>>> print (cntk.eval(cntk.ops.plus([[-30.,40.], [1.,2.]], [[-30.,40.], [1.,2.]])))
# [array([[[-60., 80.], [2., 4.]]])]
Times with broadcast of a scalar over a matrix
>>> print (cntk.eval(cntk.ops.element_times([[-30.,40.], [1.,2.]], 5)))
# [array([[[-150., 200.], [5., 10.]]])]
Args:
node (cntk.graph.ComputationNode): the node to evaluate
Returns:
numpy array containing the result
"""
from cntk.context import get_context
# call a helper method to get a context
ctx = get_context()
first = True
# the params are passed as arryas e.g. plus([1,2], [3,4]), we need to
# wrap them with input and parameter nodes
if node.params:
for p in node.params:
if p in node.inputs:
val = getattr(node, p)
# one param needs to be an Input() node. This is being fixed in
#CNTK we will remove this workaround onces we can evaluate a
#network with no inputs
if first:
if not isinstance(val, list):
# inputs have the outmost dimension for sequences
val = [val]
setattr(node, p,
input_reader([val], False, var_name=p, alias=p))
first = False
else:
setattr(node, p, constant(getattr(node, p), name=p))
return ctx.eval(node)
def eval(node):
"""
It evaluates a node that has taken a numpy array as input. Note that sequences
are not supported yet by this method
Examples:
Plus with two matrices
>>> print (cntk.eval(cntk.ops.plus([[-30.,40.], [1.,2.]], [[-30.,40.], [1.,2.]])))
# [array([[[-60., 80.], [2., 4.]]])]
Times with broadcast of a scalar over a matrix
>>> print (cntk.eval(cntk.ops.element_times([[-30.,40.], [1.,2.]], 5)))
# [array([[[-150., 200.], [5., 10.]]])]
Args:
node (cntk.graph.ComputationNode): the node to evaluate
Returns:
numpy array containing the result
"""
from cntk.context import get_context
# call a helper method to get a context
ctx = get_context()
first = True
# the params are passed as arryas e.g. plus([1,2], [3,4]), we need to
# wrap them with input and parameter nodes
if node.params:
for p in node.params:
if p in node.inputs:
val = getattr(node, p)
# one param needs to be an Input() node. This is being fixed in
#CNTK we will remove this workaround onces we can evaluate a
#network with no inputs
if first:
if not isinstance(val, list):
# inputs have the outmost dimension for sequences
val = [val]
setattr(node, p, input_reader([val], False, var_name=p, alias=p))
first = False
else:
setattr(node, p, constant(getattr(node, p), name=p))
return ctx.eval(node)
def _get_input_node(value, **kw):
# FIXME We need to better manage the context. How can we get hold
# of the overall context without having to always pass it
# explicitly?
from cntk.context import get_context
import tempfile
# We have to use NamedTemporaryFile and close it, because the obvious first
# choice, mkstemp(), would later fail in cntk.exe because the file would still be locked.
tf = tempfile.NamedTemporaryFile(prefix='_input_',
suffix='.txt',
dir=get_context().directory,
delete=False)
tf.close()
if isinstance(value, list):
value = np.asarray(value)
if len(value.shape) == 1:
# 1D list: interpret as one scalar per sample
value = value[:, np.newaxis]
if 'alias' in kw:
alias = kw['alias']
del kw['alias'] # don't confuse with constructor's parameters
else:
# TODO make sure we don't have clashes
alias = '_I_%i' % np.random.randint(1000)
with open(tf.name, 'w') as f:
f.write(_seq_to_text_format(value, alias))
from cntk.reader import CNTKTextFormatReader
input_node = cntk1_ops.Input(value.shape, **kw)
input_node.reader = CNTKTextFormatReader(tf.name)
# In case we have the shape (2,3), which will be initialized at Input() as
# '2:3', we have 2*3 = 6 dimensions when flattened out for the reader. Note
# that the first dimension is the sample.
dims = np.multiply.reduce(value.shape[:])
input_node.reader.add_input(input_node, alias, dims)
return input_node
def _get_input_node(value, **kw):
# FIXME We need to better manage the context. How can we get hold
# of the overall context without having to always pass it
# explicitly?
from cntk.context import get_context
import tempfile
# We have to use NamedTemporaryFile and close it, because the obvious first
# choice, mkstemp(), would later fail in cntk.exe because the file would still be locked.
tf = tempfile.NamedTemporaryFile(prefix="_input_", suffix=".txt", dir=get_context().directory, delete=False)
tf.close()
if isinstance(value, list):
value = np.asarray(value)
if len(value.shape) == 1:
# 1D list: interpret as one scalar per sample
value = value[:, np.newaxis]
if "alias" in kw:
alias = kw["alias"]
del kw["alias"] # don't confuse with constructor's parameters
else:
# TODO make sure we don't have clashes
alias = "_I_%i" % np.random.randint(1000)
with open(tf.name, "w") as f:
f.write(_seq_to_text_format(value, alias))
from cntk.reader import CNTKTextFormatReader
input_node = cntk1_ops.Input(value.shape, **kw)
input_node.reader = CNTKTextFormatReader(tf.name)
# In case we have the shape (2,3), which will be initialized at Input() as
# '2:3', we have 2*3 = 6 dimensions when flattened out for the reader. Note
# that the first dimension is the sample.
dims = np.multiply.reduce(value.shape[:])
input_node.reader.add_input(input_node, alias, dims)
return input_node
def _to_config_description(self):
if self.reader is None:
if not self.unmapped_nodes:
# No inputs in the graph
return ''
# We have found only inputs that were directly initialized.
# In this case, we need to serialize them into one file.
from .context import get_context
from .utils import get_temp_filename
filename = get_temp_filename(get_context().directory)
assert not self.node_map
self._serialize_unmapped_nodes(filename)
r = CNTKTextFormatReader(filename)
return r._to_config_description(self)
else:
return self.reader._to_config_description(self)
def _get_input_node(list_of_tensors, has_sequence_dimension, **kw):
'''
:param list_of_tensors: list of tensors potentially having sequences of
different lengths.
'''
# FIXME We need to better manage the context. How can we get hold
# of the overall context without having to always pass it
# explicitly?
from cntk.context import get_context
import tempfile
# We have to use NamedTemporaryFile and close it, because the obvious first
# choice, mkstemp(), would later fail in cntk.exe because the file would
# still be locked.
tf = tempfile.NamedTemporaryFile(prefix='_input_',
suffix='.txt',
dir=get_context().directory,
delete=False)
tf.close()
if 'alias' in kw:
alias = kw['alias']
del kw['alias'] # don't confuse with constructor's parameters
else:
# TODO make sure we don't have clashes
alias = '_I_%i' % np.random.randint(1000)
shapes = set()
with open(tf.name, 'w') as f:
for idx, tensor in enumerate(list_of_tensors):
if isinstance(tensor, list):
tensor = np.asarray(tensor)
if has_sequence_dimension:
# collecting the shapes ignoring the sequence dimension
shapes.add(tensor.shape[1:])
else:
shapes.add(tensor.shape)
f.write(
_tensor_to_text_format(idx, alias, tensor,
has_sequence_dimension) + '\n')
# ignoring the sequence dimension, all shapes should be equal
if len(shapes) != 1:
raise ValueError('except for the sequence dimensions all shapes ' +
'should be the same - instead we have: %s' %
(", ".join(str(s) for s in shapes)))
# shapes now contains only one shape, which has the sequence dimension
# removed.
value_shape = shapes.pop()
cntk_shape = numpy_to_cntk_shape(value_shape)
from cntk.reader import CNTKTextFormatReader
# In case we have the shape (2,3) and assuming we have only sequences of
# lengths 1, the input will be initialized with dim=3 (column major)
# followed by a reshape node that has the dims '2:3'. So we have 2*3 = 6
# dimensions when flattened out for the reader.
dims = int(np.multiply.reduce(cntk_shape))
node = cntk1_ops.Input(dims, **kw)
node.reader = CNTKTextFormatReader(tf.name)
node.reader.add_input(node, alias, dims)
if len(cntk_shape) > 1:
node = cntk1_ops.NewReshape(node, dims=cntk_shape)
return node
def _get_constant_node(value, **kw):
'''
This function creates a node that represents `value` as a constant tensor
in the graph.
To be as generic as possible, we
- flatten the data
- initialize a LearnableParameter operator with it
- ensure that the graph does not backprob to it.
- Finally we to reshape it.
'''
# FIXME We need to better manage the context. How can we get hold
# of the overall context without having to always pass it
# explicitly?
from cntk.context import get_context
import tempfile
# We have to use NamedTemporaryFile and close it, because when using the
# obvious first choice, mkstemp(), would later fail in cntk.exe because the
# file would still be locked.
# TODO make it same filename as alias
tf = tempfile.NamedTemporaryFile(prefix='_param_',
suffix='.txt',
dir=get_context().directory,
delete=False)
tf.close()
if isinstance(value, list):
value = np.asarray(value)
if len(value.shape) == 1:
# 1D list: interpret as one scalar per sample
value = value[:, np.newaxis]
if sparse.issparse(value):
raise ValueError('only dense data is supported')
with open(tf.name, 'w') as f:
# TODO value.ravel() ?
np.ndarray.flatten(value).tofile(f, sep='\n')
size = np.multiply.reduce(value.shape[:])
# The var_name specified by the user should be set to the operator that
# is finally returned, which is the shape node.
var_name = kw.pop('var_name', None)
from cntk.reader import CNTKTextFormatReader
param_node = cntk1_ops.LearnableParameter(size,
1,
learningRateMultiplier=0.0,
init='fromFile',
initFromFilePath=tf.name,
**kw)
reshape_node = cntk1_ops.NewReshape(param_node,
dims=value.shape,
var_name=var_name)
return reshape_node
