def __init__(self,
spikes=None,
network=None,
network_file=None,
window_size=1,
params=None):
object.__init__(self)
Restoreable.__init__(self)
self._window_size = window_size
if spikes is not None:
self._spikes = spikes
self._network = HopfieldNetMPF(self._spikes.N * self._window_size)
if network is not None:
self._network = network
if network_file is not None and network is None:
self._network = HopfieldNet.load(network_file)
if params is not None:
self._params = params
else:
self._params = {'Mode': 'default'}
def __init__(self,
N=None,
J=None,
theta=None,
name=None,
update="asynchronous",
symmetric=True):
object.__init__(self)
Restoreable.__init__(self)
self._learn_iterations = 0 # how many learning steps have been taken so far
self._N = N
self._symmetric = symmetric
if J is None and N > 0:
self._J = np.zeros((self._N, self._N))
else:
self._J = J
if theta is None and N > 0:
self._theta = np.zeros(self._N)
else:
self._theta = theta
self._name = name or self.__class__.__name__
self._update = update
self._neuron_order = range(self._N) if self._N else None
self._last_num_iter_for_convergence = 0 # hopfield dynamics steps previous __call__ took
self._learn_iterations = 0 # how many learning steps have been taken so far
def __init__(self,
stimulus_arr=None,
npz_file=None,
h5_file=None,
preprocess=True):
"""
Missing documentation
Parameters
----------
stimulus_arr : Type, optional
Description (default None)
npz_file : Type, optional
Description (default None)
h5_file : Type, optional
Description (default None)
preprocess : bool, optional
Description (default True)
Returns
-------
Value : Type
Description
"""
object.__init__(self)
Restoreable.__init__(self)
# TODO reuse io functionality from data module!
self.file_name = npz_file or ''
if npz_file is None and stimulus_arr is None and h5_file is None:
self._M = 0
return
if stimulus_arr is not None:
self._stimulus_arr = stimulus_arr
if npz_file is not None:
if not os.path.isfile(npz_file):
hdlog.info("File '%s' does not exist!" % npz_file)
return
self.file_name = npz_file
tmp = np.load(npz_file)
self._stimulus_arr = tmp[tmp.keys()[0]]
if h5_file is not None:
import h5py
f = h5py.File(h5_file)
self._stimulus_arr = f[f.keys()[0]]
if preprocess:
self.preprocess()
self._M = self._stimulus_arr.shape[0]
self._X = self._stimulus_arr.shape[1:]
def __init__(self, spikes=None, stimulus=None, window_size=1, learner=None):
object.__init__(self)
Restoreable.__init__(self)
self._stimulus = stimulus
self._window_size = window_size
self._learner = learner or None
self._original_spikes = spikes
self._learn_time = None
self._sample_spikes = None
self._raw_patterns = None
self._hopfield_patterns = None
self._hopfield_spikes = None
def __init__(self, spikes=None, stimulus=None, window_size=1, learner=None):
object.__init__(self)
Restoreable.__init__(self)
self._stimulus = stimulus
self._window_size = window_size
self._learner = learner or None
self._original_spikes = spikes
self._learn_time = None
self._sample_spikes = None
self._raw_patterns = None
self._hopfield_patterns = None
self._hopfield_spikes = None
def __init__(self, counter=None, save_sequence=True):
object.__init__(self)
Restoreable.__init__(self)
self._counts = {}
self._patterns = []
self._lookup_patterns = {}
self._sequence = []
self._save_sequence = save_sequence
self._skipped_patterns = 0
self._seen_sequence = []
if counter is not None:
self.merge_counts(counter)
def __init__(self, counter=None, save_sequence=True):
object.__init__(self)
Restoreable.__init__(self)
self._counts = {}
self._patterns = []
self._lookup_patterns = {}
self._sequence = []
self._save_sequence = save_sequence
self._skipped_patterns = 0
self._seen_sequence = []
if counter is not None:
self.merge_counts(counter)
def __init__(self, spikes=None, bin_size=None, preprocess=True):
object.__init__(self)
Restoreable.__init__(self)
self._spikes = np.atleast_2d(spikes)
spikes_shape = self._spikes.shape
if len(spikes_shape) == 2: # single trial
self._spikes = self._spikes.reshape((1, spikes_shape[0], spikes_shape[1]))
self._T = self._spikes.shape[0]
self._N = self._spikes.shape[1]
self._M = self._spikes.shape[2]
self._bin_size = bin_size
self._restricted = None
if preprocess:
self._preprocess()
def __init__(self, spikes=None, bin_size=None, preprocess=True):
object.__init__(self)
Restoreable.__init__(self)
self._spikes = np.atleast_2d(spikes)
spikes_shape = self._spikes.shape
if len(spikes_shape) == 2: # single trial
self._spikes = self._spikes.reshape(
(1, spikes_shape[0], spikes_shape[1]))
self._T = self._spikes.shape[0]
self._N = self._spikes.shape[1]
self._M = self._spikes.shape[2]
self._bin_size = bin_size
self._restricted = None
if preprocess:
self._preprocess()
def __init__(self, spikes=None, network=None, network_file=None, window_size=1, params=None):
object.__init__(self)
Restoreable.__init__(self)
self._window_size = window_size
if spikes is not None:
self._spikes = spikes
self._network = HopfieldNetMPF(self._spikes.N * self._window_size)
if network is not None:
self._network = network
if network_file is not None and network is None:
self._network = HopfieldNet.load(network_file)
if params is not None:
self._params = params
else:
self._params = {'Mode': 'default'}
def __init__(self, N=None, J=None, theta=None, name=None, update="asynchronous", symmetric=True):
object.__init__(self)
Restoreable.__init__(self)
self._learn_iterations = 0 # how many learning steps have been taken so far
self._N = N
self._symmetric = symmetric
if J is None and N > 0:
self._J = np.zeros((self._N, self._N))
else:
self._J = J
if theta is None and N > 0:
self._theta = np.zeros(self._N)
else:
self._theta = theta
self._name = name or self.__class__.__name__
self._update = update
self._neuron_order = range(self._N) if self._N else None
self._last_num_iter_for_convergence = 0 # hopfield dynamics steps previous __call__ took
self._learn_iterations = 0 # how many learning steps have been taken so far
def _load_v1(self, contents, load_extra=False):
# internal function to load v1 file format
hdlog.debug('loading HopfieldNet, format version 1')
return Restoreable._load_attributes(self, contents, self._SAVE_ATTRIBUTES_V1)
def _load_v1(self, contents, load_extra=False):
# internal function to load v1 file format
hdlog.debug('Loading Stimulus, format version 1')
return Restoreable._load_attributes(self, contents,
self._SAVE_ATTRIBUTES_V1)
def _load_v2(self, contents, load_extra=False):
# internal function to load v1 file format
hdlog.debug('Loading PatternsHopfield patterns, format version 2')
return Restoreable._load_attributes(self, contents,
self._SAVE_ATTRIBUTES_V2)
def _load_v2(self, contents, load_extra=False):
# internal function to load v1 file format
hdlog.debug('Loading PatternsHopfield patterns, format version 2')
return Restoreable._load_attributes(self, contents, self._SAVE_ATTRIBUTES_V2)