def __init__(self,
preprocessed_dataset,
preprocessor,
convert_to_one_hot=True,
start=None,
stop=None,
axes=['b', 0, 1, 'c']):
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
if convert_to_one_hot:
if not (self.y.min() == 0):
raise AssertionError("Expected y.min == 0 but y.min == %g" %
self.y.min())
nclass = self.y.max() + 1
y = np.zeros((self.y.shape[0], nclass), dtype='float32')
for i in xrange(self.y.shape[0]):
y[i, self.y[i]] = 1.
self.y = y
assert self.y is not None
space, source = self.data_specs
space.components[source.index('targets')].dim = nclass
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop, :]
if self.y is not None:
self.y = self.y[start:stop, :]
assert self.X.shape[0] == stop-start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
#self.mn = self.X.min()
#self.mx = self.X.max()
if getattr(preprocessor, "inv_P_", None) is None:
warnings.warn("ZCA preprocessor.inv_P_ was none. Computing "
"inverse of preprocessor.P_ now. This will take "
"some time. For efficiency, it is recommended that "
"in the future you compute the inverse in ZCA.fit() "
"instead, by passing it compute_inverse=True.")
logger.info('inverting...')
preprocessor.inv_P_ = np.linalg.inv(preprocessor.P_)
logger.info('...done inverting')
self.view_converter.set_axes(axes)
def __setstate__(self, d):
"""
.. todo::
WRITEME
"""
if d['design_loc'] is not None:
if control.get_load_data():
d['X'] = np.load(d['design_loc'])
else:
d['X'] = None
if d['compress']:
X = d['X']
mx = d['compress_max']
mn = d['compress_min']
del d['compress_max']
del d['compress_min']
d['X'] = 0
self.__dict__.update(d)
if X is not None:
self.X = np.cast['float32'](X) * mx / 255. + mn
else:
self.X = None
else:
self.__dict__.update(d)
# To be able to unpickle older data after the addition of
# the data_specs mechanism
if not all(m in d for m in ('data_specs', 'X_space',
'_iter_data_specs', 'X_topo_space')):
X_space = VectorSpace(dim=self.X.shape[1])
X_source = 'features'
if self.y is None:
space = X_space
source = X_source
else:
y_space = VectorSpace(dim=self.y.shape[-1])
y_source = 'targets'
space = CompositeSpace((X_space, y_space))
source = (X_source, y_source)
self.data_specs = (space, source)
self.X_space = X_space
self._iter_data_specs = (X_space, X_source)
view_converter = d.get('view_converter', None)
if view_converter is not None:
# Get the topo_space from the view_converter
if not hasattr(view_converter, 'topo_space'):
raise NotImplementedError("Not able to get a topo_space "
"from this converter: %s"
% view_converter)
# self.X_topo_space stores a "default" topological space that
# will be used only when self.iterator is called without a
# data_specs, and with "topo=True", which is deprecated.
self.X_topo_space = view_converter.topo_space
def from_dataset(dataset, num_examples):
"""
.. todo::
WRITEME
"""
try:
V, y = dataset.get_batch_topo(num_examples, True)
except:
# This patches a case where control.get_load_data() is false so
# dataset.X is None This logic should be removed whenever we implement
# lazy loading
if isinstance(dataset, DenseDesignMatrix) and dataset.X is None and not control.get_load_data():
warnings.warn("from_dataset wasn't able to make subset of " "dataset, using the whole thing")
return DenseDesignMatrix(X=None, view_converter=dataset.view_converter)
raise
rval = DenseDesignMatrix(topo_view=V, y=y)
rval.adjust_for_viewer = dataset.adjust_for_viewer
return rval
def __setstate__(self, d):
"""
.. todo::
WRITEME
"""
if d['design_loc'] is not None:
if control.get_load_data():
d['X'] = np.load(d['design_loc'])
else:
d['X'] = None
if d['compress']:
X = d['X']
mx = d['compress_max']
mn = d['compress_min']
del d['compress_max']
del d['compress_min']
d['X'] = 0
self.__dict__.update(d)
if X is not None:
self.X = np.cast['float32'](X) * mx / 255. + mn
else:
self.X = None
else:
self.__dict__.update(d)
# To be able to unpickle older data after the addition of
# the data_specs mechanism
if not all(m in d for m in ('data_specs', 'X_space',
'_iter_data_specs', 'X_topo_space')):
X_space = VectorSpace(dim=self.X.shape[1])
X_source = 'features'
if self.y is None:
space = X_space
source = X_source
else:
y_space = VectorSpace(dim=self.y.shape[-1])
y_source = 'targets'
space = CompositeSpace((X_space, y_space))
source = (X_source, y_source)
self.data_specs = (space, source)
self.X_space = X_space
self._iter_data_specs = (X_space, X_source)
view_converter = d.get('view_converter', None)
if view_converter is not None:
# Get the topo_space from the view_converter
if not hasattr(view_converter, 'topo_space'):
raise NotImplementedError("Not able to get a topo_space "
"from this converter: %s"
% view_converter)
# self.X_topo_space stores a "default" topological space that
# will be used only when self.iterator is called without a
# data_specs, and with "topo=True", which is deprecated.
self.X_topo_space = view_converter.topo_space
def __init__(self,
preprocessed_dataset,
preprocessor,
convert_to_one_hot=True,
start=None,
stop=None,
axes=['b', 0, 1, 'c']):
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
if convert_to_one_hot:
if not (self.y.min() == 0):
raise AssertionError("Expected y.min == 0 but y.min == %g" %
self.y.min())
nclass = self.y.max() + 1
y = np.zeros((self.y.shape[0], nclass), dtype='float32')
for i in xrange(self.y.shape[0]):
y[i, self.y[i]] = 1.
self.y = y
assert self.y is not None
space, source = self.data_specs
space.components[source.index('targets')].dim = nclass
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop, :]
if self.y is not None:
self.y = self.y[start:stop, :]
assert self.X.shape[0] == stop - start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
#self.mn = self.X.min()
#self.mx = self.X.max()
if preprocessor.inv_P_ is None:
warnings.warn("ZCA preprocessor.inv_P_ was none. Computing "
"inverse of preprocessor.P_ now. This will take "
"some time. For efficiency, it is recommended that "
"in the future you compute the inverse in ZCA.fit() "
"instead, by passing it compute_inverse=True.")
logger.info('inverting...')
preprocessor.inv_P_ = np.linalg.inv(preprocessor.P_)
logger.info('...done inverting')
self.view_converter.set_axes(axes)
def from_dataset(dataset, num_examples):
"""
.. todo::
WRITEME
"""
try:
V, y = dataset.get_batch_topo(num_examples, True)
except:
# This patches a case where control.get_load_data() is false so
# dataset.X is None This logic should be removed whenever we implement
# lazy loading
if isinstance(dataset, DenseDesignMatrix) and \
dataset.X is None and \
not control.get_load_data():
warnings.warn("from_dataset wasn't able to make subset of "
"dataset, using the whole thing")
return DenseDesignMatrix(X=None,
view_converter=dataset.view_converter)
raise
rval = DenseDesignMatrix(topo_view=V, y=y)
rval.adjust_for_viewer = dataset.adjust_for_viewer
return rval
def __init__(self,
preprocessed_dataset,
preprocessor,
start=None,
stop=None,
axes=None):
if axes is not None:
warnings.warn("The axes argument to ZCA_Dataset no longer has "
"any effect. Its role is now carried out by the "
"Space you pass to Dataset.iterator. You should "
"remove 'axes' arguments from calls to "
"ZCA_Dataset. This argument may be removed from "
"the library after 2015-05-05.")
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
self.y_labels = preprocessed_dataset.y_labels
# Defined up here because PEP8 requires excessive indenting if defined
# where it is used.
msg = ("Expected self.y to have dim 2, but it has %d. Maybe you are "
"loading from an outdated pickle file?")
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop, :]
if self.y is not None:
if self.y.ndim != 2:
raise ValueError(msg % self.y.ndim)
self.y = self.y[start:stop, :]
assert self.X.shape[0] == stop - start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
if getattr(preprocessor, "inv_P_", None) is None:
warnings.warn("ZCA preprocessor.inv_P_ was none. Computing "
"inverse of preprocessor.P_ now. This will take "
"some time. For efficiency, it is recommended that "
"in the future you compute the inverse in ZCA.fit() "
"instead, by passing it compute_inverse=True.")
logger.info('inverting...')
preprocessor.inv_P_ = np.linalg.inv(preprocessor.P_)
logger.info('...done inverting')
def __init__(self,
preprocessed_dataset,
preprocessor,
start=None,
stop=None,
axes=None):
if axes is not None:
warnings.warn("The axes argument to ZCA_Dataset no longer has "
"any effect. Its role is now carried out by the "
"Space you pass to Dataset.iterator. You should "
"remove 'axes' arguments from calls to "
"ZCA_Dataset. This argument may be removed from "
"the library after 2015-05-05.")
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
self.y_labels = preprocessed_dataset.y_labels
# Defined up here because PEP8 requires excessive indenting if defined
# where it is used.
msg = ("Expected self.y to have dim 2, but it has %d. Maybe you are "
"loading from an outdated pickle file?")
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop, :]
if self.y is not None:
if self.y.ndim != 2:
raise ValueError(msg % self.y.ndim)
self.y = self.y[start:stop, :]
assert self.X.shape[0] == stop - start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
if getattr(preprocessor, "inv_P_", None) is None:
warnings.warn("ZCA preprocessor.inv_P_ was none. Computing "
"inverse of preprocessor.P_ now. This will take "
"some time. For efficiency, it is recommended that "
"in the future you compute the inverse in ZCA.fit() "
"instead, by passing it compute_inverse=True.")
logger.info('inverting...')
preprocessor.inv_P_ = np.linalg.inv(preprocessor.P_)
logger.info('...done inverting')
def __init__(self,
preprocessed_dataset,
preprocessor,
convert_to_one_hot=True,
start=None,
stop=None,
axes=['b', 0, 1, 'c']):
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
if convert_to_one_hot:
if not (self.y.min() == 0):
raise AssertionError("Expected y.min == 0 but y.min == " +
str(self.y.min()))
nclass = self.y.max() + 1
y = np.zeros((self.y.shape[0], nclass), dtype='float32')
for i in xrange(self.y.shape[0]):
y[i, self.y[i]] = 1.
self.y = y
assert self.y is not None
space, source = self.data_specs
space.components[source.index('targets')].dim = nclass
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop, :]
if self.y is not None:
self.y = self.y[start:stop, :]
assert self.X.shape[0] == stop - start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
#self.mn = self.X.min()
#self.mx = self.X.max()
print 'inverting...'
preprocessor.invert()
print '...done inverting'
self.view_converter.axes = axes
def __init__(self,
preprocessed_dataset,
preprocessor,
convert_to_one_hot = True,
start = None,
stop = None,
axes = ['b', 0, 1, 'c']):
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
if convert_to_one_hot:
if not ( self.y.min() == 0):
raise AssertionError("Expected y.min == 0 but y.min == "+str(self.y.min()))
nclass = self.y.max() + 1
y = np.zeros((self.y.shape[0], nclass), dtype='float32')
for i in xrange(self.y.shape[0]):
y[i,self.y[i]] = 1.
self.y = y
assert self.y is not None
space, source = self.data_specs
space.components[source.index('targets')].dim = nclass
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop,:]
if self.y is not None:
self.y = self.y[start:stop,:]
assert self.X.shape[0] == stop-start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
#self.mn = self.X.min()
#self.mx = self.X.max()
print 'inverting...'
preprocessor.invert()
print '...done inverting'
self.view_converter.axes = axes
def __init__(self,
preprocessed_dataset,
preprocessor,
start=None,
stop=None,
axes=['b', 0, 1, 'c']):
"""
.. todo::
WRITEME
"""
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
self.y_labels = preprocessed_dataset.y_labels
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop, :]
if self.y is not None:
self.y = self.y[start:stop, :]
assert self.X.shape[0] == stop - start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
# self.mn = self.X.min()
# self.mx = self.X.max()
if getattr(preprocessor, "inv_P_", None) is None:
warnings.warn("ZCA preprocessor.inv_P_ was none. Computing "
"inverse of preprocessor.P_ now. This will take "
"some time. For efficiency, it is recommended that "
"in the future you compute the inverse in ZCA.fit() "
"instead, by passing it compute_inverse=True.")
logger.info('inverting...')
preprocessor.inv_P_ = np.linalg.inv(preprocessor.P_)
logger.info('...done inverting')
self.view_converter.set_axes(axes)
def __init__(self, which_set='train', center=False, start=None, stop=None,
axes=['b', 'c', 0, 1], preprocessor=None,
fit_preprocessor=False, fit_test_preprocessor=False):
self.shape = (8, 35, 57)
self.size = {'train': 2849, 'valid': 2849, 'test': 2849}
self.range = (-10, 10)
self.path = "${PYLEARN2_DATA_PATH}/ecmwf/"
self.set_path = {'train': 'ecmwf.train', 'valid': 'ecmwf.val', 'test': 'ecmwf.test'}
self.args = locals()
if which_set not in ['train', 'valid', 'test']:
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["train","valid","test"].')
path = self.path + self.set_path[which_set]
if control.get_load_data():
path = serial.preprocess(path)
datasetCache = cache.datasetCache
path = datasetCache.cache_file(path)
X, topo_view, y = self._read_ecmwf(path, which_set)
else:
X = np.random.rand(self.size[which_set], np.prod(self.shape))
topo_view = np.random.rand(self.size[which_set]*np.prod(self.shape))
y = np.random.randint(self.range[0], self.range[1], (self.size[which_set], 1))
(m, v, r, c) = topo_view.shape
if center:
topo_view -= topo_view.mean(axis=0)
super(ECMWF, self).__init__(X=X, topo_view=topo_view, y=y, axes=axes)
assert not np.any(np.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop=' + str(stop) + '>' +
'm=' + str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d"
% (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
if which_set == 'test':
assert fit_test_preprocessor is None or \
(fit_preprocessor == fit_test_preprocessor)
if self.X is not None and preprocessor:
preprocessor.apply(self, fit_preprocessor)
def __init__(self, which_set, center = False,
one_hot = False, binarize = False,
axes=['b', 0, 1, 'c'],
preprocessor = ZCA(),
fit_preprocessor = False,
fit_test_preprocessor = False):
self.args = locals()
print "==========IIII LOVVEEEE YOOOOOUU========"
def dimshuffle(b01c):
default = ('b', 0, 1, 'c')
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = os.environ['PYLEARN2_DATA_PATH'] + '/faceEmo/'
if which_set == 'train':
X = np.load(path + 'train_X.npy').astype('float32')
y = np.load(path + 'train_y.npy').astype('float32')
else:
# import pdb
# pdb.set_trace()
assert which_set == 'test'
X = np.load(path + 'test_X.npy').astype('float32')
y = np.load(path + 'test_y.npy').astype('float32')
if binarize:
X = (X > 0.5).astype('float32')
self.one_hot = one_hot
if one_hot:
one_hot = np.zeros((y.shape[0],3),dtype='float32')
for i in xrange(y.shape[0]):
one_hot[i,y[i]] = 1.
y = one_hot
if center:
X -= X.mean(axis=0)
super(FaceEmo,self).__init__(X = X, y = y)
if which_set == 'test':
assert fit_test_preprocessor is None or (fit_preprocessor == fit_test_preprocessor)
if self.X is not None and preprocessor:
preprocessor.fit(self.X)
preprocessor.apply(self, fit_preprocessor)
def __init__(self,
preprocessed_dataset,
preprocessor,
start=None,
stop=None,
axes=None):
if axes is not None:
warnings.warn("The axes argument to ZCA_Dataset no longer has "
"any effect. Its role is now carried out by the "
"Space you pass to Dataset.iterator. You should "
"remove 'axes' arguments from calls to "
"ZCA_Dataset. This argument may be removed from "
"the library after 2015-05-05.")
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
self.y_labels = preprocessed_dataset.y_labels
# Defined up here because PEP8 requires excessive indenting if defined
# where it is used.
msg = ("Expected self.y to have dim 2, but it has %d. Maybe you are "
"loading from an outdated pickle file?")
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop, :]
if self.y is not None:
if self.y.ndim != 2:
raise ValueError(msg % self.y.ndim)
self.y = self.y[start:stop, :]
assert self.X.shape[0] == stop - start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
def __init__(self,
preprocessed_dataset,
preprocessor,
start=None,
stop=None,
axes=None):
if axes is not None:
warnings.warn("The axes argument to ZCA_Dataset no longer has "
"any effect. Its role is now carried out by the "
"Space you pass to Dataset.iterator. You should "
"remove 'axes' arguments from calls to "
"ZCA_Dataset. This argument may be removed from "
"the library after 2015-05-05.")
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
self.y_labels = preprocessed_dataset.y_labels
# Defined up here because PEP8 requires excessive indenting if defined
# where it is used.
msg = ("Expected self.y to have dim 2, but it has %d. Maybe you are "
"loading from an outdated pickle file?")
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop, :]
if self.y is not None:
if self.y.ndim != 2:
raise ValueError(msg % self.y.ndim)
self.y = self.y[start:stop, :]
assert self.X.shape[0] == stop - start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
def from_dataset(dataset, num_examples):
# This function does not support tags attribute
try:
V, y = dataset.get_batch_topo(num_examples, True)
except:
if isinstance(dataset, DenseDesignMatrix) and dataset.X is None and not control.get_load_data():
warnings.warn("from_dataset wasn't able to make subset of dataset, using the whole thing")
return DenseDesignMatrix(X = None, view_converter = dataset.view_converter)
#This patches a case where control.get_load_data() is false so dataset.X is None
#This logic should be removed whenever we implement lazy loading
raise
rval = DenseDesignMatrix(topo_view=V, y=y)
rval.adjust_for_viewer = dataset.adjust_for_viewer
return rval
def _load_path(self, which_set, which_targets, word2vec_dict={}):
if which_targets not in ['fine', 'coarse']:
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["fine","coarse"].')
if which_set not in ['train', 'test']:
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["train","test"].')
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/TREC_question_type_data/"
if which_set == 'train':
data_path = path + 'trecqc.train_5500.label.txt'
else:
assert which_set == 'test'
data_path = path + 'trecqc.test_500.label.txt'
data_path = serial.preprocess(data_path)
self.path = path
return data_path
def __setstate__(self, d):
if d["design_loc"] is not None:
if control.get_load_data():
d["X"] = N.load(d["design_loc"])
else:
d["X"] = None
if d["compress"]:
X = d["X"]
mx = d["compress_max"]
mn = d["compress_min"]
del d["compress_max"]
del d["compress_min"]
d["X"] = 0
self.__dict__.update(d)
if X is not None:
self.X = N.cast["float32"](X) * mx / 255.0 + mn
else:
self.X = None
else:
self.__dict__.update(d)
def __setstate__(self, d):
if d['design_loc'] is not None:
if control.get_load_data():
d['X'] = N.load(d['design_loc'])
else:
d['X'] = None
if d['compress']:
X = d['X']
mx = d['compress_max']
mn = d['compress_min']
del d['compress_max']
del d['compress_min']
d['X'] = 0
self.__dict__.update(d)
if X is not None:
self.X = N.cast['float32'](X) * mx / 255. + mn
else:
self.X = None
else:
self.__dict__.update(d)
def __setstate__(self, d):
if d['design_loc'] is not None:
if control.get_load_data():
d['X'] = N.load(d['design_loc'])
else:
d['X'] = None
if d['compress']:
X = d['X']
mx = d['compress_max']
mn = d['compress_min']
del d['compress_max']
del d['compress_min']
d['X'] = 0
self.__dict__.update(d)
if X is not None:
self.X = N.cast['float32'](X) * mx / 255. + mn
else:
self.X = None
else:
self.__dict__.update(d)
def __init__(self, which_set, start=None, stop=None):
self.args = locals()
if which_set not in ['train', 'test']:
raise ValueError('Unrecognized which_set value "%s".' %
(which_set, ) +
'". Valid values are ["train","test"].')
size = TEST_SIZE if which_set == 'test' else TRAIN_SIZE
if control.get_load_data():
topo_view, y = read_images(IM_GLOB, size, TEST_TRAIN_RANDOM_SEED,
False if which_set == 'train' else True)
else:
topo_view = np.random.rand(size, 32, 32)
y = np.random.randint(0, 10, (size, 1))
super(PlanktonDDM, self).__init__(topo_view=topo_view,
y=y,
axes=['b', 0, 1, 'c'],
y_labels=NUM_CLASSES)
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop=' + str(stop) + '>' + 'm=' +
str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d" %
(self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
def __init__(
self,
which_set,
center=False,
shuffle=False,
one_hot=False,
binarize=False,
start=None,
stop=None,
axes=["b", 0, 1, "c"],
preprocessor=None,
fit_preprocessor=False,
fit_test_preprocessor=False,
):
self.args = locals()
if which_set not in ["train", "test"]:
if which_set == "valid":
raise ValueError(
"There is no such thing as the MNIST validation set. MNIST"
"consists of 60,000 train examples and 10,000 test"
"examples. If you wish to use a validation set you should"
"divide the train set yourself. The pylearn2 dataset"
"implements and will only ever implement the standard"
"train / test split used in the literature."
)
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) + '". Valid values are ["train","test"].'
)
def dimshuffle(b01c):
default = ("b", 0, 1, "c")
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = "${VIDTIMIT}/data/"
if which_set == "train":
im_path = path + "train.npy"
label_path = path + "train-labels.npy"
else:
assert which_set == "test"
im_path = path + "test.npy"
label_path = path + "test-labels.npy"
# Path substitution done here in order to make the lower-level
# mnist_ubyte.py as stand-alone as possible (for reuse in, e.g.,
# the Deep Learning Tutorials, or in another package).
im_path = serial.preprocess(im_path)
label_path = serial.preprocess(label_path)
topo_view = np.load(im_path)
y = np.load(label_path)
if binarize:
topo_view = (topo_view > 0.5).astype("float32")
self.one_hot = one_hot
if one_hot:
one_hot = N.zeros((y.shape[0], 36), dtype="float32")
for i in xrange(y.shape[0]):
one_hot[i, y[i]] = 1.0
y = one_hot
max_labels = None
else:
max_labels = 36
m, r, c = topo_view.shape
assert r == 32
assert c == 32
topo_view = topo_view.reshape(m, r, c, 1)
if which_set == "train":
assert m == 27280
elif which_set == "test":
assert m == 10929
else:
assert False
if center:
topo_view -= topo_view.mean(axis=0)
if shuffle:
self.shuffle_rng = make_np_rng(None, [1, 2, 3], which_method="shuffle")
for i in xrange(topo_view.shape[0]):
j = self.shuffle_rng.randint(m)
# Copy ensures that memory is not aliased.
tmp = topo_view[i, :, :, :].copy()
topo_view[i, :, :, :] = topo_view[j, :, :, :]
topo_view[j, :, :, :] = tmp
# Note: slicing with i:i+1 works for one_hot=True/False
tmp = y[i : i + 1].copy()
y[i] = y[j]
y[j] = tmp
super(VidTIMIT, self).__init__(topo_view=dimshuffle(topo_view), y=y, axes=axes, max_labels=max_labels)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError("stop=" + str(stop) + ">" + "m=" + str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d" % (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
else:
# data loading is disabled, just make something that defines the
# right topology
topo = dimshuffle(np.zeros((1, 32, 32, 1)))
super(VidTIMIT, self).__init__(topo_view=topo, axes=axes)
self.X = None
if which_set == "test":
assert fit_test_preprocessor is None or (fit_preprocessor == fit_test_preprocessor)
if self.X is not None and preprocessor:
preprocessor.apply(self, fit_preprocessor)
def __init__(self, which_set, center=False, shuffle=False, one_hot=False, binarize=False, start=None, stop=None):
self.args = locals()
if which_set not in ["train", "test"]:
if which_set == "valid":
raise ValueError(
"There is no such thing as the MNIST "
"validation set. MNIST consists of 60,000 train examples and 10,000 test"
" examples. If you wish to use a validation set you should divide the train "
"set yourself. The pylearn2 dataset implements and will only ever implement "
"the standard train / test split used in the literature."
)
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) + '". Valid values are ["train","test"].'
)
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/mnist/"
if which_set == "train":
im_path = path + "train-images-idx3-ubyte"
label_path = path + "train-labels-idx1-ubyte"
else:
assert which_set == "test"
im_path = path + "t10k-images-idx3-ubyte"
label_path = path + "t10k-labels-idx1-ubyte"
# Path substitution done here in order to make the lower-level
# mnist_ubyte.py as stand-alone as possible (for reuse in, e.g.,
# the Deep Learning Tutorials, or in another package).
im_path = serial.preprocess(im_path)
label_path = serial.preprocess(label_path)
topo_view = read_mnist_images(im_path, dtype="float32")
y = read_mnist_labels(label_path)
if binarize:
topo_view = (topo_view > 0.5).astype("float32")
self.one_hot = one_hot
if one_hot:
one_hot = N.zeros((y.shape[0], 10), dtype="float32")
for i in xrange(y.shape[0]):
one_hot[i, y[i]] = 1.0
y = one_hot
m, r, c = topo_view.shape
assert r == 28
assert c == 28
topo_view = topo_view.reshape(m, r, c, 1)
if which_set == "train":
assert m == 60000
elif which_set == "test":
assert m == 10000
else:
assert False
if center:
topo_view -= topo_view.mean(axis=0)
if shuffle:
self.shuffle_rng = np.random.RandomState([1, 2, 3])
for i in xrange(topo_view.shape[0]):
j = self.shuffle_rng.randint(m)
# Copy ensures that memory is not aliased.
tmp = topo_view[i, :, :, :].copy()
topo_view[i, :, :, :] = topo_view[j, :, :, :]
topo_view[j, :, :, :] = tmp
# Note: slicing with i:i+1 works for both one_hot=True/False.
tmp = y[i : i + 1].copy()
y[i] = y[j]
y[j] = tmp
view_converter = dense_design_matrix.DefaultViewConverter((28, 28, 1))
super(MNIST, self).__init__(topo_view=topo_view, y=y)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError("stop=" + str(stop) + ">" + "m=" + str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d" % (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
else:
# data loading is disabled, just make something that defines the right topology
topo = np.zeros((1, 28, 28, 1))
super(MNIST, self).__init__(topo_view=topo)
self.X = None
def __init__(self, which_set, center=False, shuffle=False,
binarize=False, start=None, stop=None,
axes=['b', 0, 1, 'c'],
preprocessor=None,
fit_preprocessor=False,
fit_test_preprocessor=False):
self.args = locals()
if which_set not in ['train', 'test']:
if which_set == 'valid':
raise ValueError(
"There is no such thing as the MNIST validation set. MNIST"
"consists of 60,000 train examples and 10,000 test"
"examples. If you wish to use a validation set you should"
"divide the train set yourself. The pylearn2 dataset"
"implements and will only ever implement the standard"
"train / test split used in the literature.")
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["train","test"].')
def dimshuffle(b01c):
"""
.. todo::
WRITEME
"""
default = ('b', 0, 1, 'c')
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/sign24/"
if which_set == 'train':
im_path = path + 'train-images-idx3-ubyte'
label_path = path + 'train-labels-idx1-ubyte'
else:
assert which_set == 'test'
im_path = path + 't10k-images-idx3-ubyte'
label_path = path + 't10k-labels-idx1-ubyte'
# Path substitution done here in order to make the lower-level
# mnist_ubyte.py as stand-alone as possible (for reuse in, e.g.,
# the Deep Learning Tutorials, or in another package).
im_path = serial.preprocess(im_path)
label_path = serial.preprocess(label_path)
# Locally cache the files before reading them
datasetCache = cache.datasetCache
im_path = datasetCache.cache_file(im_path)
label_path = datasetCache.cache_file(label_path)
topo_view = read_mnist_images(im_path, dtype='float32')
y = np.atleast_2d(read_mnist_labels(label_path)).T
else:
if which_set == 'train':
size = 15
elif which_set == 'test':
size = 5
else:
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["train","test"].')
topo_view = np.random.rand(size, 28, 28)
y = np.random.randint(0, 10, (size, 1))
if binarize:
topo_view = (topo_view > 0.5).astype('float32')
y_labels = 24
m, r, c = topo_view.shape
assert r == 28
assert c == 28
topo_view = topo_view.reshape(m, r, c, 1)
if which_set == 'train':
assert m == 3576
elif which_set == 'test':
assert m == 1176
else:
assert False
if center:
topo_view -= topo_view.mean(axis=0)
if shuffle:
self.shuffle_rng = make_np_rng(
None, [1, 2, 3], which_method="shuffle")
for i in xrange(topo_view.shape[0]):
j = self.shuffle_rng.randint(m)
# Copy ensures that memory is not aliased.
tmp = topo_view[i, :, :, :].copy()
topo_view[i, :, :, :] = topo_view[j, :, :, :]
topo_view[j, :, :, :] = tmp
tmp = y[i:i + 1].copy()
y[i] = y[j]
y[j] = tmp
super(MNIST, self).__init__(topo_view=dimshuffle(topo_view), y=y,
axes=axes, y_labels=y_labels)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop=' + str(stop) + '>' +
'm=' + str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d"
% (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
if which_set == 'test':
assert fit_test_preprocessor is None or \
(fit_preprocessor == fit_test_preprocessor)
if self.X is not None and preprocessor:
preprocessor.apply(self, fit_preprocessor)
def __init__(self, which_set, center=False, shuffle=False,
one_hot=None, binarize=False, start=None,
stop=None, axes=['b', 0, 1, 'c'],
preprocessor=None,
fit_preprocessor=False,
fit_test_preprocessor=False):
self.args = locals()
if which_set not in ['train', 'test']:
if which_set == 'valid':
raise ValueError(
"There is no such thing as the MNIST validation set. MNIST"
"consists of 60,000 train examples and 10,000 test"
"examples. If you wish to use a validation set you should"
"divide the train set yourself. The pylearn2 dataset"
"implements and will only ever implement the standard"
"train / test split used in the literature.")
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["train","test"].')
def dimshuffle(b01c):
"""
.. todo::
WRITEME
"""
default = ('b', 0, 1, 'c')
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/mnist/"
if which_set == 'train':
im_path = path + 'train-images-idx3-ubyte'
label_path = path + 'train-labels-idx1-ubyte'
else:
assert which_set == 'test'
im_path = path + 't10k-images-idx3-ubyte'
label_path = path + 't10k-labels-idx1-ubyte'
# Path substitution done here in order to make the lower-level
# mnist_ubyte.py as stand-alone as possible (for reuse in, e.g.,
# the Deep Learning Tutorials, or in another package).
im_path = serial.preprocess(im_path)
label_path = serial.preprocess(label_path)
# Locally cache the files before reading them
datasetCache = cache.datasetCache
im_path = datasetCache.cache_file(im_path)
label_path = datasetCache.cache_file(label_path)
topo_view = read_mnist_images(im_path, dtype='float32')
y = np.atleast_2d(read_mnist_labels(label_path)).T
else:
if which_set == 'train':
size = 60000
elif which_set == 'test':
size = 10000
else:
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["train","test"].')
topo_view = np.random.rand(size, 28, 28)
y = np.random.randint(0, 10, (size, 1))
if binarize:
topo_view = (topo_view > 0.5).astype('float32')
max_labels = 10
if one_hot is not None:
warnings.warn("the `one_hot` parameter is deprecated. To get "
"one-hot encoded targets, request that they "
"live in `VectorSpace` through the `data_specs` "
"parameter of MNIST's iterator method. "
"`one_hot` will be removed on or after "
"September 20, 2014.", stacklevel=2)
m, r, c = topo_view.shape
assert r == 28
assert c == 28
topo_view = topo_view.reshape(m, r, c, 1)
if which_set == 'train':
assert m == 60000
elif which_set == 'test':
assert m == 10000
else:
assert False
if center:
topo_view -= topo_view.mean(axis=0)
if shuffle:
self.shuffle_rng = make_np_rng(None, [1, 2, 3], which_method="shuffle")
for i in xrange(topo_view.shape[0]):
j = self.shuffle_rng.randint(m)
# Copy ensures that memory is not aliased.
tmp = topo_view[i, :, :, :].copy()
topo_view[i, :, :, :] = topo_view[j, :, :, :]
topo_view[j, :, :, :] = tmp
# Note: slicing with i:i+1 works for one_hot=True/False
tmp = y[i:i+1].copy()
y[i] = y[j]
y[j] = tmp
super(MNIST, self).__init__(topo_view=dimshuffle(topo_view), y=y,
axes=axes, y_labels=max_labels)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop=' + str(stop) + '>' +
'm=' + str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d"
% (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
if which_set == 'test':
assert fit_test_preprocessor is None or \
(fit_preprocessor == fit_test_preprocessor)
if self.X is not None and preprocessor:
preprocessor.apply(self, fit_preprocessor)
def __init__(self,
which_set,
start=None,
stop=None,
axes=['b', 0, 1, 'c']):
self.args = locals()
def dimshuffle(b01c):
default = ('b', 0, 1, 'c')
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = "/local/Pylearn2/data/ADNI/"
im_path = path + 'ADNI_X_down'
label_path = path + 'ADNI_y_down'
#im_path = serial.preprocess(im_path)
#label_path = serial.preprocess(label_path)
#Locally cache the files before reading them
datasetCache = cache.datasetCache
im_path = datasetCache.cache_file(im_path)
label_path = datasetCache.cache_file(label_path)
with open_if_filename(im_path, 'rb') as f:
#magic, number, rows, cols = struct.unpack('>iiii', f.read(16))
#im_array = N.fromfile(f, dtype='float64')
im_array = pickle.load(f)
with open_if_filename(label_path, 'rb') as f:
#label_array = N.fromfile(f, dtype='uint8')
label_array = pickle.load(f)
topo_view = im_array
y = label_array
else:
if which_set == 'train':
size = 397
else:
size = 50
topo_view = np.random.rand(size, 64, 64, 41)
y = np.random.randint(0, 3, (size, 1))
y_labels = 3
m, r, c, d = topo_view.shape
assert r == 64
assert c == 64
topo_view = topo_view.reshape(m, r, c, 41)
if which_set == 'train':
assert m == 397
else:
assert m == 50
super(MRI, self).__init__(topo_view=dimshuffle(topo_view),
y=y,
axes=axes,
y_labels=y_labels)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
#if stop > self.X.shape[0]:
#raise ValueError('stop=' + str(stop) + '>' + 'm=' + str(self.X.shape=[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d" %
(self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
def __init__(self,
which_set,
center=False,
shuffle=False,
one_hot=False,
binarize=False,
start=None,
stop=None,
axes=['b', 0, 1, 'c'],
preprocessor=None,
fit_preprocessor=False,
fit_test_preprocessor=False):
self.args = locals()
if which_set not in ['train', 'test']:
if which_set == 'valid':
raise ValueError(
"There is no such thing as the MNIST validation set. MNIST"
"consists of 60,000 train examples and 10,000 test"
"examples. If you wish to use a validation set you should"
"divide the train set yourself. The pylearn2 dataset"
"implements and will only ever implement the standard"
"train / test split used in the literature.")
raise ValueError('Unrecognized which_set value "%s".' %
(which_set, ) +
'". Valid values are ["train","test"].')
def dimshuffle(b01c):
default = ('b', 0, 1, 'c')
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/mnist/"
if which_set == 'train':
im_path = path + 'train-images-idx3-ubyte'
label_path = path + 'train-labels-idx1-ubyte'
else:
assert which_set == 'test'
im_path = path + 't10k-images-idx3-ubyte'
label_path = path + 't10k-labels-idx1-ubyte'
# Path substitution done here in order to make the lower-level
# mnist_ubyte.py as stand-alone as possible (for reuse in, e.g.,
# the Deep Learning Tutorials, or in another package).
im_path = serial.preprocess(im_path)
label_path = serial.preprocess(label_path)
topo_view = read_mnist_images(im_path, dtype='float32')
y = read_mnist_labels(label_path)
if binarize:
topo_view = (topo_view > 0.5).astype('float32')
self.one_hot = one_hot
if one_hot:
one_hot = N.zeros((y.shape[0], 10), dtype='float32')
for i in xrange(y.shape[0]):
one_hot[i, y[i]] = 1.
y = one_hot
max_labels = None
else:
max_labels = 10
m, r, c = topo_view.shape
assert r == 28
assert c == 28
topo_view = topo_view.reshape(m, r, c, 1)
if which_set == 'train':
assert m == 60000
elif which_set == 'test':
assert m == 10000
else:
assert False
if center:
topo_view -= topo_view.mean(axis=0)
if shuffle:
self.shuffle_rng = make_np_rng(None, [1, 2, 3],
which_method="shuffle")
for i in xrange(topo_view.shape[0]):
j = self.shuffle_rng.randint(m)
# Copy ensures that memory is not aliased.
tmp = topo_view[i, :, :, :].copy()
topo_view[i, :, :, :] = topo_view[j, :, :, :]
topo_view[j, :, :, :] = tmp
# Note: slicing with i:i+1 works for one_hot=True/False
tmp = y[i:i + 1].copy()
y[i] = y[j]
y[j] = tmp
super(MNIST, self).__init__(topo_view=dimshuffle(topo_view),
y=y,
axes=axes,
max_labels=max_labels)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop=' + str(stop) + '>' + 'm=' +
str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d" %
(self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
else:
# data loading is disabled, just make something that defines the
# right topology
topo = dimshuffle(np.zeros((1, 28, 28, 1)))
super(MNIST, self).__init__(topo_view=topo, axes=axes)
self.X = None
if which_set == 'test':
assert fit_test_preprocessor is None or \
(fit_preprocessor == fit_test_preprocessor)
if self.X is not None and preprocessor:
preprocessor.apply(self, fit_preprocessor)
def __init__(self,
preprocessed_dataset,
preprocessor,
convert_to_one_hot=None,
start=None,
stop=None,
axes=['b', 0, 1, 'c']):
"""
.. todo::
WRITEME
"""
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
self.y_labels = preprocessed_dataset.y_labels
if convert_to_one_hot is not None:
warnings.warn(
"the `convert_to_one_hot` parameter is deprecated. To get "
"one-hot encoded targets, request that they "
"live in `VectorSpace` through the `data_specs` "
"parameter of dataset iterator method. "
"`convert_to_one_hot` will be removed on or after "
"September 20, 2014.",
stacklevel=2)
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop, :]
if self.y is not None:
self.y = self.y[start:stop, :]
assert self.X.shape[0] == stop - start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
#self.mn = self.X.min()
#self.mx = self.X.max()
if getattr(preprocessor, "inv_P_", None) is None:
warnings.warn("ZCA preprocessor.inv_P_ was none. Computing "
"inverse of preprocessor.P_ now. This will take "
"some time. For efficiency, it is recommended that "
"in the future you compute the inverse in ZCA.fit() "
"instead, by passing it compute_inverse=True.")
logger.info('inverting...')
preprocessor.inv_P_ = np.linalg.inv(preprocessor.P_)
logger.info('...done inverting')
self.view_converter.set_axes(axes)
def __init__(self,
which_set,
center=False,
shuffle=False,
one_hot=False,
binarize=False,
start=None,
stop=None):
self.args = locals()
if which_set not in ['train', 'test']:
if which_set == 'valid':
raise ValueError(
"There is no such thing as the MNIST "
"validation set. MNIST consists of 60,000 train examples and 10,000 test"
" examples. If you wish to use a validation set you should divide the train "
"set yourself. The pylearn2 dataset implements and will only ever implement "
"the standard train / test split used in the literature.")
raise ValueError('Unrecognized which_set value "%s".' %
(which_set, ) +
'". Valid values are ["train","test"].')
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/mnist/"
if which_set == 'train':
im_path = path + 'train-images-idx3-ubyte'
label_path = path + 'train-labels-idx1-ubyte'
else:
assert which_set == 'test'
im_path = path + 't10k-images-idx3-ubyte'
label_path = path + 't10k-labels-idx1-ubyte'
topo_view = read_mnist_images(im_path, dtype='float32')
y = read_mnist_labels(label_path)
if binarize:
topo_view = (topo_view > 0.5).astype('float32')
self.one_hot = one_hot
if one_hot:
one_hot = N.zeros((y.shape[0], 10), dtype='float32')
for i in xrange(y.shape[0]):
one_hot[i, y[i]] = 1.
y = one_hot
m, r, c = topo_view.shape
assert r == 28
assert c == 28
topo_view = topo_view.reshape(m, r, c, 1)
if which_set == 'train':
assert m == 60000
elif which_set == 'test':
assert m == 10000
else:
assert False
if center:
topo_view -= topo_view.mean(axis=0)
if shuffle:
self.shuffle_rng = np.random.RandomState([1, 2, 3])
for i in xrange(topo_view.shape[0]):
j = self.shuffle_rng.randint(m)
# Copy ensures that memory is not aliased.
tmp = topo_view[i, :, :, :].copy()
topo_view[i, :, :, :] = topo_view[j, :, :, :]
topo_view[j, :, :, :] = tmp
# Note: slicing with i:i+1 works for both one_hot=True/False.
tmp = y[i:i + 1].copy()
y[i] = y[j]
y[j] = tmp
view_converter = dense_design_matrix.DefaultViewConverter(
(28, 28, 1))
super(MNIST, self).__init__(topo_view=topo_view, y=y)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop=' + str(stop) + '>' + 'm=' +
str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d" %
(self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
else:
#data loading is disabled, just make something that defines the right topology
topo = np.zeros((1, 28, 28, 1))
super(MNIST, self).__init__(topo_view=topo)
self.X = None
def __setstate__(self, d):
if d['design_loc'] is not None:
if control.get_load_data():
d['X'] = N.load(d['design_loc'])
else:
d['X'] = None
if d['compress']:
X = d['X']
mx = d['compress_max']
mn = d['compress_min']
del d['compress_max']
del d['compress_min']
d['X'] = 0
self.__dict__.update(d)
if X is not None:
self.X = N.cast['float32'](X) * mx / 255. + mn
else:
self.X = None
else:
self.__dict__.update(d)
# To be able to unpickle older data after the addition of
# the data_specs mechanism
if not all(m in d for m in ('data_specs', 'X_space',
'_iter_data_specs', 'X_topo_space')):
X_space = VectorSpace(dim=self.X.shape[1])
X_source = 'features'
if self.y is None:
space = X_space
source = X_source
else:
y_space = VectorSpace(dim=self.y.shape[-1])
y_source = 'targets'
space = CompositeSpace((X_space, y_space))
source = (X_source, y_source)
self.data_specs = (space, source)
self.X_space = X_space
self._iter_data_specs = (X_space, X_source)
view_converter = d.get('view_converter', None)
if view_converter is not None:
# Build a Conv2DSpace from the view_converter
if not (isinstance(view_converter, DefaultViewConverter)
and len(view_converter.shape) == 3):
raise NotImplementedError(
"Not able to build a Conv2DSpace "
"corresponding to this converter: %s"
% view_converter)
axes = view_converter.axes
rows, cols, channels = view_converter.shape
# self.X_topo_space stores a "default" topological space that
# will be used only when self.iterator is called without a
# data_specs, and with "topo=True", which is deprecated.
self.X_topo_space = Conv2DSpace(
shape=(rows, cols), num_channels=channels, axes=axes)
def __init__(self, which_set, shuffle=False,
start=None, stop=None, axes=['b', 0, 1, 'c'],
preprocessor=None, fit_preprocessor=False,
fit_test_preprocessor=False):
self.args = locals()
if which_set not in ['train', 'valid', 'test']:
raise ValueError('Unrecognized which_set value "%s".' %
(which_set,) + '". Valid values are ' +
'["train", "valid", "test"].')
def dimshuffle(b01c):
default = ('b', 0, 1, 'c')
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/binarized_mnist/binarized_mnist_" + \
which_set + ".npy"
im_path = serial.preprocess(path)
# Locally cache the files before reading them
datasetCache = cache.datasetCache
im_path = datasetCache.cache_file(im_path)
try:
X = serial.load(im_path)
except IOError:
raise NotInstalledError("BinarizedMNIST data files cannot be "
"found in ${PYLEARN2_DATA_PATH}. Run "
"pylearn2/scripts/datasets/"
"download_binarized_mnist.py to get "
"the data")
else:
if which_set == 'train':
size = 50000
else:
size = 10000
X = numpy.random.binomial(n=1, p=0.5, size=(size, 28 ** 2))
m, d = X.shape
assert d == 28 ** 2
if which_set == 'train':
assert m == 50000
else:
assert m == 10000
if shuffle:
self.shuffle_rng = make_np_rng(None, [1, 2, 3],
which_method="shuffle")
for i in xrange(X.shape[0]):
j = self.shuffle_rng.randint(m)
# Copy ensures that memory is not aliased.
tmp = X[i, :].copy()
X[i, :] = X[j, :]
X[j, :] = tmp
super(BinarizedMNIST, self).__init__(
X=X,
view_converter=DefaultViewConverter(shape=(28, 28, 1))
)
assert not numpy.any(numpy.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop=' + str(stop) + '>' +
'm=' + str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d"
% (self.X.shape[0], start, stop))
if which_set == 'test':
assert fit_test_preprocessor is None or \
(fit_preprocessor == fit_test_preprocessor)
if self.X is not None and preprocessor:
preprocessor.apply(self, fit_preprocessor)
def __init__(self, which_set, center = False, shuffle = False,
one_hot = False, binarize = False):
if which_set not in ['train','test']:
if which_set == 'valid':
raise ValueError("There is no such thing as the MNIST "
"validation set. MNIST consists of 60,000 train examples and 10,000 test"
" examples. If you wish to use a validation set you should divide the train "
"set yourself. The pylearn2 dataset implements and will only ever implement "
"the standard train / test split used in the literature.")
raise ValueError('Unrecognized which_set value "%s".' %
(which_set,)+'". Valid values are ["train","test"].')
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/mnist/"
if which_set == 'train':
im_path = path + 'train-images-idx3-ubyte'
label_path = path + 'train-labels-idx1-ubyte'
else:
assert which_set == 'test'
im_path = path + 't10k-images-idx3-ubyte'
label_path = path + 't10k-labels-idx1-ubyte'
topo_view = read_mnist_images(im_path, dtype='float32')
y = read_mnist_labels(label_path)
if binarize:
topo_view = ( topo_view > 0.5).astype('float32')
self.one_hot = one_hot
if one_hot:
one_hot = N.zeros((y.shape[0],10),dtype='float32')
for i in xrange(y.shape[0]):
one_hot[i,y[i]] = 1.
y = one_hot
m, r, c = topo_view.shape
assert r == 28
assert c == 28
topo_view = topo_view.reshape(m,r,c,1)
if which_set == 'train':
assert m == 60000
elif which_set == 'test':
assert m == 10000
else:
assert False
if center:
topo_view -= topo_view.mean(axis=0)
if shuffle:
self.shuffle_rng = np.random.RandomState([1,2,3])
for i in xrange(topo_view.shape[0]):
j = self.shuffle_rng.randint(m)
tmp = topo_view[i,:,:,:]
topo_view[i,:,:,:] = topo_view[j,:,:,:]
topo_view[j,:,:,:] = tmp
tmp = y[i]
y[i] = y[j]
y[j] = tmp
view_converter = dense_design_matrix.DefaultViewConverter((28,28,1))
super(MNIST,self).__init__(topo_view = topo_view , y = y)
assert not N.any(N.isnan(self.X))
else:
#data loading is disabled, just make something that defines the right topology
topo = np.zeros((1,28,28,1))
super(MNIST,self).__init__(topo_view = topo)
self.X = None
def __init__(self,
preprocessed_dataset,
preprocessor,
convert_to_one_hot=None,
start=None,
stop=None,
axes=['b', 0, 1, 'c']):
"""
.. todo::
WRITEME
"""
self.args = locals()
self.preprocessed_dataset = preprocessed_dataset
self.preprocessor = preprocessor
self.rng = self.preprocessed_dataset.rng
self.data_specs = preprocessed_dataset.data_specs
self.X_space = preprocessed_dataset.X_space
self.X_topo_space = preprocessed_dataset.X_topo_space
self.view_converter = preprocessed_dataset.view_converter
self.y = preprocessed_dataset.y
self.y_labels = preprocessed_dataset.y_labels
if convert_to_one_hot is not None:
warnings.warn("the `convert_to_one_hot` parameter is deprecated. To get "
"one-hot encoded targets, request that they "
"live in `VectorSpace` through the `data_specs` "
"parameter of dataset iterator method. "
"`convert_to_one_hot` will be removed on or after "
"September 20, 2014.", stacklevel=2)
if control.get_load_data():
if start is not None:
self.X = preprocessed_dataset.X[start:stop, :]
if self.y is not None:
self.y = self.y[start:stop, :]
assert self.X.shape[0] == stop-start
else:
self.X = preprocessed_dataset.X
else:
self.X = None
if self.X is not None:
if self.y is not None:
assert self.y.shape[0] == self.X.shape[0]
#self.mn = self.X.min()
#self.mx = self.X.max()
if getattr(preprocessor, "inv_P_", None) is None:
warnings.warn("ZCA preprocessor.inv_P_ was none. Computing "
"inverse of preprocessor.P_ now. This will take "
"some time. For efficiency, it is recommended that "
"in the future you compute the inverse in ZCA.fit() "
"instead, by passing it compute_inverse=True.")
logger.info('inverting...')
preprocessor.inv_P_ = np.linalg.inv(preprocessor.P_)
logger.info('...done inverting')
self.view_converter.set_axes(axes)
def __setstate__(self, d):
if d['design_loc'] is not None:
if control.get_load_data():
d['X'] = N.load(d['design_loc'])
else:
d['X'] = None
if d['compress']:
X = d['X']
mx = d['compress_max']
mn = d['compress_min']
del d['compress_max']
del d['compress_min']
d['X'] = 0
self.__dict__.update(d)
if X is not None:
self.X = N.cast['float32'](X) * mx / 255. + mn
else:
self.X = None
else:
self.__dict__.update(d)
# To be able to unpickle older data after the addition of
# the data_specs mechanism
if not all(m in d for m in ('data_specs', 'X_space',
'_iter_data_specs', 'X_topo_space')):
X_space = VectorSpace(dim=self.X.shape[1])
X_source = 'features'
if self.y is None:
space = X_space
source = X_source
else:
y_space = VectorSpace(dim=self.y.shape[-1])
y_source = 'targets'
space = CompositeSpace((X_space, y_space))
source = (X_source, y_source)
self.data_specs = (space, source)
self.X_space = X_space
self._iter_data_specs = (X_space, X_source)
view_converter = d.get('view_converter', None)
if view_converter is not None:
# Build a Conv2DSpace from the view_converter
if not (isinstance(view_converter, DefaultViewConverter)
and len(view_converter.shape) == 3):
raise NotImplementedError(
"Not able to build a Conv2DSpace "
"corresponding to this converter: %s" % view_converter)
axes = view_converter.axes
rows, cols, channels = view_converter.shape
# self.X_topo_space stores a "default" topological space that
# will be used only when self.iterator is called without a
# data_specs, and with "topo=True", which is deprecated.
self.X_topo_space = Conv2DSpace(shape=(rows, cols),
num_channels=channels,
axes=axes)
def __init__(self, which_set, imgd=65, zd=1, ds=1, center = False, shuffle = False,
one_hot = False, binarize = False, start = None,
stop = None, axes=['b', 0, 1, 'c'],
preprocessor = None,
fit_preprocessor = False,
fit_test_preprocessor = False):
self.args = locals()
if which_set not in ['train','valid','test']:
raise ValueError('Unrecognized which_set value "%s".' %
(which_set,)+'". Valid values are ["train","valid",test"].')
def dimshuffle(b01c):
default = ('b', 0, 1, 'c')
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/lgn/"
path = path + "LGN1_MembraneSamples_65x65x1_mp0.50_train50000_valid10000_test10000_seed11.pkl.gz"
path = serial.preprocess(path)
f = gzip.open(path, 'rb')
train_set, valid_set, test_set = cPickle.load(f)
f.close()
if which_set == 'train':
data = train_set
elif which_set == 'valid':
data = valid_set
else:
data = test_set
input_shape = (imgd, imgd, zd)
# f = h5py.file(path, 'r')
# input_shape = f['input_shape'][...]
# if which_set == 'train':
# data = f['/train_set'][...]
# elif which_set == 'valid':
# data = f['/valid_set'][...]
# else:
# data = f['/test_set'][...]
# Convert images to float 0-1
topo_view = data[0].astype(np.float32) / 255.0
y = data[1]
self.one_hot = one_hot
if one_hot:
one_hot = N.zeros((y.shape[0],2),dtype='float32')
for i in xrange(y.shape[0]):
one_hot[i,y[i]] = 1.
y = one_hot
m = topo_view.shape[0]
rows, cols, slices = input_shape
topo_view = topo_view.reshape(m, rows, cols, slices)
if center:
topo_view -= topo_view.mean(axis=0)
if shuffle:
self.shuffle_rng = np.random.RandomState([1,2,3])
for i in xrange(topo_view.shape[0]):
j = self.shuffle_rng.randint(m)
# Copy ensures that memory is not aliased.
tmp = topo_view[i,:,:,:].copy()
topo_view[i,:,:,:] = topo_view[j,:,:,:]
topo_view[j,:,:,:] = tmp
# Note: slicing with i:i+1 works for both one_hot=True/False.
tmp = y[i:i+1].copy()
y[i] = y[j]
y[j] = tmp
super(LGN,self).__init__(topo_view = dimshuffle(topo_view), y = y, axes=axes)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop='+str(stop)+'>'+'m='+str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop,:]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d" % (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop,:]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
else:
#data loading is disabled, just make something that defines the right topology
topo = dimshuffle(np.zeros((1,65,65,1)))
super(LGN,self).__init__(topo_view = topo, axes=axes)
self.X = None
if which_set == 'test':
assert fit_test_preprocessor is None or (fit_preprocessor == fit_test_preprocessor)
if self.X is not None and preprocessor:
preprocessor.apply(self, fit_preprocessor)
def __init__(self, which_set, imgd=49, zd=1, ds=1, center = False, shuffle = False,
one_hot = False, binarize = False, start = None,
stop = None, axes=['b', 0, 1, 'c'],
preprocessor = None,
fit_preprocessor = False,
fit_test_preprocessor = False):
self.args = locals()
if which_set not in ['train','valid','test']:
raise ValueError('Unrecognized which_set value "%s".' %
(which_set,)+'". Valid values are ["train","valid",test"].')
def dimshuffle(b01c):
default = ('b', 0, 1, 'c')
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/ISBI_2012/"
path = path + "ISBI_MembraneSamples_49x49_mp0.50_train50000_valid5000_test5000_seed11_ds2b.pkl.gz"
path = serial.preprocess(path)
f = gzip.open(path, 'rb')
train_set, valid_set, test_set = cPickle.load(f)
f.close()
if which_set == 'train':
data = train_set
elif which_set == 'valid':
data = valid_set
else:
data = test_set
input_shape = (imgd, imgd, zd)
# f = h5py.file(path, 'r')
# input_shape = f['input_shape'][...]
# if which_set == 'train':
# data = f['/train_set'][...]
# elif which_set == 'valid':
# data = f['/valid_set'][...]
# else:
# data = f['/test_set'][...]
# Convert images to float 0-1
topo_view = data[0].astype(np.float32) / 255.0
y = data[1]
self.one_hot = one_hot
if one_hot:
one_hot = N.zeros((y.shape[0],2),dtype='float32')
for i in xrange(y.shape[0]):
one_hot[i,y[i]] = 1.
y = one_hot
m = topo_view.shape[0]
rows, cols, slices = input_shape
topo_view = topo_view.reshape(m, rows, cols, slices)
if center:
topo_view -= topo_view.mean(axis=0)
if shuffle:
self.shuffle_rng = np.random.RandomState([1,2,3])
for i in xrange(topo_view.shape[0]):
j = self.shuffle_rng.randint(m)
# Copy ensures that memory is not aliased.
tmp = topo_view[i,:,:,:].copy()
topo_view[i,:,:,:] = topo_view[j,:,:,:]
topo_view[j,:,:,:] = tmp
# Note: slicing with i:i+1 works for both one_hot=True/False.
tmp = y[i:i+1].copy()
y[i] = y[j]
y[j] = tmp
super(ISBI,self).__init__(topo_view = dimshuffle(topo_view), y = y, axes=axes)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop='+str(stop)+'>'+'m='+str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop,:]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d" % (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop,:]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
else:
#data loading is disabled, just make something that defines the right topology
topo = dimshuffle(np.zeros((1,49,49,1)))
super(ISBI,self).__init__(topo_view = topo, axes=axes)
self.X = None
if which_set == 'test':
assert fit_test_preprocessor is None or (fit_preprocessor == fit_test_preprocessor)
if self.X is not None and preprocessor:
preprocessor.apply(self, fit_preprocessor)
def __init__(self, which_set, start=None, stop=None, axes=['b', 0, 1, 'c']):
self.args = locals()
def dimshuffle(b01c):
default = ('b', 0, 1, 'c')
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = "/local/Pylearn2/data/ADNI/"
im_path = path + 'ADNI_X_down'
label_path = path + 'ADNI_y_down'
#im_path = serial.preprocess(im_path)
#label_path = serial.preprocess(label_path)
#Locally cache the files before reading them
datasetCache = cache.datasetCache
im_path = datasetCache.cache_file(im_path)
label_path = datasetCache.cache_file(label_path)
with open_if_filename(im_path, 'rb') as f:
#magic, number, rows, cols = struct.unpack('>iiii', f.read(16))
#im_array = N.fromfile(f, dtype='float64')
im_array = pickle.load(f)
with open_if_filename(label_path, 'rb') as f:
#label_array = N.fromfile(f, dtype='uint8')
label_array = pickle.load(f)
topo_view = im_array
y = label_array
else:
if which_set == 'train':
size = 397
else:
size = 50
topo_view = np.random.rand(size, 64, 64, 41)
y = np.random.randint(0, 3, (size, 1))
y_labels = 3
m, r, c, d = topo_view.shape
assert r == 64
assert c == 64
topo_view = topo_view.reshape(m, r, c, 41)
if which_set == 'train':
assert m == 397
else:
assert m == 50
super(MRI, self).__init__(topo_view=dimshuffle(topo_view), y=y,
axes=axes, y_labels=y_labels)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
#if stop > self.X.shape[0]:
#raise ValueError('stop=' + str(stop) + '>' + 'm=' + str(self.X.shape=[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d"
% (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
def __init__(self, which_set, start=None, stop=None):
self.args = locals()
if which_set not in ['train','valid', 'test']:
if which_set == 'valid':
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["train","test"].')
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/milleniumSAMs/"
if which_set == 'train':
data_path = path + 'milliTrain.pickle.gz'
elif which_set == 'valid':
data_path = path + 'milliValid.pickle.gz'
else:
assert which_set == 'test'
data_path = path + 'milliTest.pickle.gz'
# Path substitution done here in order to make the lower-level
# mnist_ubyte.py as stand-alone as possible (for reuse in, e.g.,
# the Deep Learning Tutorials, or in another package).
data_path = serial.preprocess(data_path)
# Locally cache the files before reading them
#Not sure if it's necessary, but why not?
datasetCache = cache.datasetCache
data_path = datasetCache.cache_file(data_path)
X, y = pickle.load(gzip.open(data_path))
else:
#I don't know when this would be called, or why?
#It should generate random data of the same dimensions, but I'm not gonna bother doing that.
#This is the old code for the MNIST images
if which_set == 'train':
size = 60000
elif which_set == 'test':
size = 10000
else:
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["train","test"].')
topo_view = np.random.rand(size, 28, 28)
y = np.random.randint(0, 10, (size, 1))
m, r = X.shape
assert r == 193
#Shuffle used to be here, which I don't think is terrifically necessary
#X=dimshuffle(X)
super(MILLI_SAM, self).__init__(X=X, y=y)
assert not np.any(np.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop=' + str(stop) + '>' +
'm=' + str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d"
% (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
def __init__(self, which_set, center = False, shuffle = False,
one_hot = False, binarize = False, start = None,
stop = None, axes=['b', 0, 1, 'c'],
preprocessor = None,
fit_preprocessor = False,
fit_test_preprocessor = False):
self.args = locals()
if which_set not in ['train','test']:
if which_set == 'valid':
raise ValueError("There is no such thing as the MNIST "
"validation set. MNIST consists of 60,000 train examples and 10,000 test"
" examples. If you wish to use a validation set you should divide the train "
"set yourself. The pylearn2 dataset implements and will only ever implement "
"the standard train / test split used in the literature.")
raise ValueError('Unrecognized which_set value "%s".' %
(which_set,)+'". Valid values are ["train","test"].')
def dimshuffle(b01c):
default = ('b', 0, 1, 'c')
return b01c.transpose(*[default.index(axis) for axis in axes])
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/mnist/"
if which_set == 'train':
im_path = path + 'train-images-idx3-ubyte'
label_path = path + 'train-labels-idx1-ubyte'
else:
assert which_set == 'test'
im_path = path + 't10k-images-idx3-ubyte'
label_path = path + 't10k-labels-idx1-ubyte'
# Path substitution done here in order to make the lower-level
# mnist_ubyte.py as stand-alone as possible (for reuse in, e.g.,
# the Deep Learning Tutorials, or in another package).
im_path = serial.preprocess(im_path)
label_path = serial.preprocess(label_path)
topo_view = read_mnist_images(im_path, dtype='float32')
y = read_mnist_labels(label_path)
if binarize:
topo_view = ( topo_view > 0.5).astype('float32')
self.one_hot = one_hot
if one_hot:
one_hot = N.zeros((y.shape[0],10),dtype='float32')
for i in xrange(y.shape[0]):
one_hot[i,y[i]] = 1.
y = one_hot
m, r, c = topo_view.shape
assert r == 28
assert c == 28
topo_view = topo_view.reshape(m,r,c,1)
if which_set == 'train':
assert m == 60000
elif which_set == 'test':
assert m == 10000
else:
assert False
if center:
topo_view -= topo_view.mean(axis=0)
if shuffle:
self.shuffle_rng = np.random.RandomState([1,2,3])
for i in xrange(topo_view.shape[0]):
j = self.shuffle_rng.randint(m)
# Copy ensures that memory is not aliased.
tmp = topo_view[i,:,:,:].copy()
topo_view[i,:,:,:] = topo_view[j,:,:,:]
topo_view[j,:,:,:] = tmp
# Note: slicing with i:i+1 works for both one_hot=True/False.
tmp = y[i:i+1].copy()
y[i] = y[j]
y[j] = tmp
super(MNIST,self).__init__(topo_view = dimshuffle(topo_view), y = y, axes=axes)
assert not N.any(N.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop='+str(stop)+'>'+'m='+str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop,:]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d" % (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop,:]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
else:
# data loading is disabled, just make something that defines the
# right topology
topo = dimshuffle(np.zeros((1,28,28,1)))
super(MNIST,self).__init__(topo_view = topo, axes=axes)
self.X = None
if which_set == 'test':
assert fit_test_preprocessor is None or (fit_preprocessor == fit_test_preprocessor)
if self.X is not None and preprocessor:
preprocessor.apply(self, fit_preprocessor)
def __init__(self, which_set, start=None, stop=None, nParticles = None):
self.args = locals()
if which_set not in ['train','valid', 'test']:
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["train","test", "valid"].')
if control.get_load_data():
path = "${PYLEARN2_DATA_PATH}/nanoParticle/"
#have to load in the whole array from the start anyway
import h5py
import numpy as np
totParticles = 262144
if nParticles is None:
nParticles = totParticles
trainingFrac = .8
validFrac = .1
np.random.seed(0)
idxs = np.random.choice(totParticles, nParticles)
#if which_set == 'train':
slice = np.s_[idxs, :]
#elif which_set == 'valid':
# slice = np.s_[int(totParticles*trainingFrac):int(totParticles*trainingFrac)+nParticles, :]
#else:
# assert which_set == 'test'
# slice = np.s_[int(totParticles*(trainingFrac+validFrac)):int(totParticles*(trainingFrac+validFrac))+nParticles, :]
X = np.zeros((100, nParticles*6))
y = np.zeros((100, nParticles*3))
colors = ['b', 'g','r','y','k','m']
def getFilename(i):
base = path+'snapshot_'
if i<10:
out= base+'00%d.hdf5'%i
elif i<100:
out= base+'0%d.hdf5'%i
else:
out= base+'%d.hdf5'%i
return serial.preprocess(out)
absMinVel, absMaxVal = 0,0
maxCoord= 10000 #particles in a 0-10000 cube
for i in xrange(101):
fname = getFilename(i)
f = h5py.File(fname, 'r')
ids = f['PartType1']['ParticleIDs'][()]
sorter = ids.argsort()
coords = f['PartType1']['Coordinates'][()]
coords = coords[sorter]#sort by ids
#normalize
#coordinates are all >=0, so just divide by max
coords/=maxCoord
#from matplotlib import pyplot as plt
#plt.scatter(coords[0, 0], coords[0,1], c = colors[i%len(colors)])
coords = coords[slice]
#if i == 100:
# print which_set
# plt.show()
if i!=0:
y[i-1,:] = coords.flatten()
#if i == 100:
# continue
#y[i,:] = coords.flatten()
if i!=100:
vels = f['PartType1']['Velocities'][()]
vels = vels[sorter]
minVel, maxVel = vels.min(), vels.max()
if minVel < absMinVel:
absMinVel = minVel
if maxVel > absMaxVal:
absMaxVal = maxVel
vels = vels[slice]
data = np.concatenate((coords, vels), axis = 1).flatten()
X[i,:] = data
del data
del coords
f.close()
#normalize the velocity columns
for n in xrange(nParticles):
for col in xrange(3):
X[:, n*6+3+col] = (X[:, n*6+3+col]-absMinVel)/(absMaxVal-absMinVel)
else:
#I don't know when this would be called, or why?
#It should generate random data of the same dimensions, but I'm not gonna bother doing that.
#This is the old code for the MNIST images
if which_set == 'train':
size = 60000
elif which_set == 'test':
size = 10000
else:
raise ValueError(
'Unrecognized which_set value "%s".' % (which_set,) +
'". Valid values are ["train","test"].')
topo_view = np.random.rand(size, 28, 28)
y = np.random.randint(0, 10, (size, 1))
m, r = X.shape
assert m == 100
n, s = y.shape
assert n == 100
#Shuffle used to be here, which I don't think is terrifically necessary
#X=dimshuffle(X)
super(NANO_PARTICLE, self).__init__(X=X, y=y)
del X
del y
assert not np.any(np.isnan(self.X))
if start is not None:
assert start >= 0
if stop > self.X.shape[0]:
raise ValueError('stop=' + str(stop) + '>' +
'm=' + str(self.X.shape[0]))
assert stop > start
self.X = self.X[start:stop, :]
if self.X.shape[0] != stop - start:
raise ValueError("X.shape[0]: %d. start: %d stop: %d"
% (self.X.shape[0], start, stop))
if len(self.y.shape) > 1:
self.y = self.y[start:stop, :]
else:
self.y = self.y[start:stop]
assert self.y.shape[0] == stop - start
