def __init__(self, k, nvis, convergence_th=1e-6, max_iter=None,
verbose=False):
"""
Parameters
----------
k : int
Number of clusters
nvis : int
Dimension of input
convergence_th : float
Threshold of distance to clusters under which k-means stops \
iterating.
max_iter : int
Maximum number of iterations. Defaults to infinity.
"""
Block.__init__(self)
Model.__init__(self)
self.input_space = VectorSpace(nvis)
self.k = k
self.convergence_th = convergence_th
if max_iter:
if max_iter < 0:
raise Exception('KMeans init: max_iter should be positive.')
self.max_iter = max_iter
else:
self.max_iter = float('inf')
self.verbose = verbose
def test_stackedblocks_without_params():
"""
Test StackedBlocks when not all layers have trainable params
"""
sb = StackedBlocks([Block(), Block()])
assert sb._params is None
def __init__(self, C, kernel='rbf', gamma=1.0, coef0=1.0, degree=3):
estimator = SVC(C=C,
kernel=kernel,
gamma=gamma,
coef0=coef0,
degree=degree)
Block.__init__(self)
Model.__init__(self)
super(DenseMulticlassSVM, self).__init__(estimator)
def __init__(self, k, nvis, convergence_th=1e-6, max_iter=None, verbose=False):
Block.__init__(self)
Model.__init__(self)
self.input_space = VectorSpace(nvis)
self.k = k
self.convergence_th = convergence_th
if max_iter:
if max_iter < 0:
raise Exception("KMeans init: max_iter should be positive.")
self.max_iter = max_iter
else:
self.max_iter = float("inf")
self.verbose = verbose
def __init__(self, k, nvis, convergence_th=1e-6, max_iter=None,
verbose=False):
Block.__init__(self)
Model.__init__(self)
self.input_space = VectorSpace(nvis)
self.k = k
self.convergence_th = convergence_th
if max_iter:
if max_iter < 0:
raise Exception('KMeans init: max_iter should be positive.')
self.max_iter = max_iter
else:
self.max_iter = float('inf')
self.verbose = verbose
def test_transformer_iterator():
"""
Tests whether TransformerIterator is iterable
"""
test_path = os.path.join(pylearn2.__path__[0], 'datasets', 'tests',
'test.csv')
raw = CSVDataset(path=test_path, expect_headers=False)
block = Block()
dataset = TransformerDataset(raw, block)
iterator = dataset.iterator('shuffled_sequential', 3)
try:
iter(iterator)
except TypeError:
assert False, "TransformerIterator isn't iterable"
# Set PCA subclass from argument.
if args.algorithm == 'cov_eig':
PCAImpl = CovEigPCA
elif args.algorithm == 'svd':
PCAImpl = SVDPCA
elif args.algorithm == 'online':
PCAImpl = OnlinePCA
conf['minibatch_size'] = args.minibatch_size
else:
# This should never happen.
raise NotImplementedError(args.algorithm)
# Load precomputed PCA transformation if requested; otherwise compute it.
if args.load_file:
pca = Block.load(args.load_file)
else:
logger.info("... computing PCA")
pca = PCAImpl(**conf)
pca.train(train_data)
# Save the computed transformation.
pca.save(args.save_file)
# Apply the transformation to test and valid subsets.
inputs = tensor.matrix()
pca_transform = theano.function([inputs], pca(inputs))
valid_pca = pca_transform(valid_data)
test_pca = pca_transform(test_data)
logger.info("New shapes: {0}".format(map(numpy.shape,
[valid_pca, test_pca])))
# Set PCA subclass from argument.
if args.algorithm == 'cov_eig':
PCAImpl = CovEigPCA
elif args.algorithm == 'svd':
PCAImpl = SVDPCA
elif args.algorithm == 'online':
PCAImpl = OnlinePCA
conf['minibatch_size'] = args.minibatch_size
else:
# This should never happen.
raise NotImplementedError(args.algorithm)
# Load precomputed PCA transformation if requested; otherwise compute it.
if args.load_file:
pca = Block.load(args.load_file)
else:
logger.info("... computing PCA")
pca = PCAImpl(**conf)
pca.train(train_data)
# Save the computed transformation.
pca.save(args.save_file)
# Apply the transformation to test and valid subsets.
inputs = tensor.matrix()
pca_transform = theano.function([inputs], pca(inputs))
valid_pca = pca_transform(valid_data)
test_pca = pca_transform(test_data)
logger.info("New shapes: {0}".format(map(numpy.shape,
[valid_pca, test_pca])))
def __init__(self, C, kernel='rbf', gamma = 1.0, coef0 = 1.0, degree = 3):
estimator = SVC(C=C, kernel=kernel, gamma = gamma, coef0 = coef0,
degree = degree)
Block.__init__(self)
Model.__init__(self)
super(DenseMulticlassSVM,self).__init__(estimator)
def __init__(self,
nmap,
input_space=None,
nvisx=None,
nvisy=None,
input_source=("featuresX", "featuresY"),
act_enc=None,
act_dec=None,
irange=1e-3,
rng=9001):
Block.__init__(self)
Model.__init__(self)
assert nmap > 0, "Number of mapping units must be positive"
if nvisx is not None and nvisy is not None or input_space is not None:
if nvisx is not None and nvisy is not None:
assert nvisx > 0, "Number of visx units must be non-negative"
assert nvisy > 0, "Number of visy units must be non-negative"
input_space = CompositeSpace(
[VectorSpace(nvisx),
VectorSpace(nvisy)])
self.nvisx = nvisx
self.nvisy = nvisy
elif isinstance(input_space.components[0], Conv2DSpace):
rx, cx = input_space.components[0].shape
chx = input_space.components[0].num_channels
ry, cy = input_space.components[1].shape
chy = input_space.components[1].num_channels
self.nvisx = rx * cx * chx
self.nvisy = ry * cy * chy
else:
raise NotImplementedError(
str(type(self)) + " does not support that input_space.")
# Check whether the input_space and input_source structures match
try:
DataSpecsMapping((input_space, input_source))
except ValueError:
raise ValueError("The structures of `input_space`, %s, and "
"`input_source`, %s do not match. If you "
"specified a CompositeSpace as an input, "
"be sure to specify the data sources as well." %
(input_space, input_source))
self.input_space = input_space
self.input_source = input_source
self.nmap = nmap
self.output_space = VectorSpace(self.nmap)
self._initialize_visbiasX(self.nvisx) # self.visbiasX
self._initialize_visbiasY(self.nvisy) # self.visbiasY
self._initialize_mapbias() # self.mapbias
self.irange = irange
self.rng = make_np_rng(rng, which_method="randn")
seed = int(self.rng.randint(2**30))
self.s_rng = make_theano_rng(seed, which_method="uniform")
def _resolve_callable(conf, conf_attr):
if conf[conf_attr] is None or conf[conf_attr] == "linear":
return None
# If it's a callable, use it directly.
if hasattr(conf[conf_attr], '__call__'):
return conf[conf_attr]
elif (conf[conf_attr] in globals()
and hasattr(globals()[conf[conf_attr]], '__call__')):
return globals()[conf[conf_attr]]
elif hasattr(tensor.nnet, conf[conf_attr]):
return getattr(tensor.nnet, conf[conf_attr])
elif hasattr(tensor, conf[conf_attr]):
return getattr(tensor, conf[conf_attr])
else:
raise ValueError("Couldn't interpret %s value: '%s'" %
(conf_attr, conf[conf_attr]))
self.act_enc = _resolve_callable(locals(), 'act_enc')
self.act_dec = _resolve_callable(locals(), 'act_dec')
def __init__(
self,
nmap,
input_space=None,
nvisx=None,
nvisy=None,
input_source=("featuresX", "featuresY"),
act_enc=None,
act_dec=None,
irange=1e-3,
rng=9001,
):
Block.__init__(self)
Model.__init__(self)
assert nmap > 0, "Number of mapping units must be positive"
if nvisx is not None and nvisy is not None or input_space is not None:
if nvisx is not None and nvisy is not None:
assert nvisx > 0, "Number of visx units must be non-negative"
assert nvisy > 0, "Number of visy units must be non-negative"
input_space = CompositeSpace([VectorSpace(nvisx), VectorSpace(nvisy)])
self.nvisx = nvisx
self.nvisy = nvisy
elif isinstance(input_space.components[0], Conv2DSpace):
rx, cx = input_space.components[0].shape
chx = input_space.components[0].num_channels
ry, cy = input_space.components[1].shape
chy = input_space.components[1].num_channels
self.nvisx = rx * cx * chx
self.nvisy = ry * cy * chy
else:
raise NotImplementedError(str(type(self)) + " does not support that input_space.")
# Check whether the input_space and input_source structures match
try:
DataSpecsMapping((input_space, input_source))
except ValueError:
raise ValueError(
"The structures of `input_space`, %s, and "
"`input_source`, %s do not match. If you "
"specified a CompositeSpace as an input, "
"be sure to specify the data sources as well." % (input_space, input_source)
)
self.input_space = input_space
self.input_source = input_source
self.nmap = nmap
self.output_space = VectorSpace(self.nmap)
self._initialize_visbiasX(self.nvisx) # self.visbiasX
self._initialize_visbiasY(self.nvisy) # self.visbiasY
self._initialize_mapbias() # self.mapbias
self.irange = irange
self.rng = make_np_rng(rng, which_method="randn")
seed = int(self.rng.randint(2 ** 30))
self.s_rng = make_theano_rng(seed, which_method="uniform")
def _resolve_callable(conf, conf_attr):
if conf[conf_attr] is None or conf[conf_attr] == "linear":
return None
# If it's a callable, use it directly.
if hasattr(conf[conf_attr], "__call__"):
return conf[conf_attr]
elif conf[conf_attr] in globals() and hasattr(globals()[conf[conf_attr]], "__call__"):
return globals()[conf[conf_attr]]
elif hasattr(tensor.nnet, conf[conf_attr]):
return getattr(tensor.nnet, conf[conf_attr])
elif hasattr(tensor, conf[conf_attr]):
return getattr(tensor, conf[conf_attr])
else:
raise ValueError("Couldn't interpret %s value: '%s'" % (conf_attr, conf[conf_attr]))
self.act_enc = _resolve_callable(locals(), "act_enc")
self.act_dec = _resolve_callable(locals(), "act_dec")
