def build_convolution(self, layer, weights=None):
delay = self.config.getfloat('cell', 'delay')
transpose_kernel = \
self.config.get('simulation', 'keras_backend') == 'tensorflow'
conns, biases = build_convolution(layer, delay, transpose_kernel)
connections = np.array(conns)
self.set_biases(biases)
print("Connecting layer...")
self.connections[-1].connect(i=connections[:, 0].astype('int64'),
j=connections[:, 1].astype('int64'))
w = connections[:, 2] if weights is None else weights.flatten()
self.connections[-1].w = w
def build_convolution(self, layer, input_weight=None):
from snntoolbox.simulation.utils import build_convolution
delay = self.config.getfloat('cell', 'delay')
transpose_kernel = \
self.config.get('simulation', 'keras_backend') == 'tensorflow'
self._conns, self._biases = build_convolution(layer, delay,
transpose_kernel)
self.set_biases()
print("Connecting layer...")
for conn in self._conns:
i = conn[0]
j = conn[1]
self.connections[-1].connect(i=i, j=j)
if input_weight is not None:
self.connections[-1].w = input_weight.flatten()
else:
self.connections[-1].w[i, j] = conn[2]
def build_convolution(self, layer):
from snntoolbox.simulation.utils import build_convolution
delay = self.config.getfloat('cell', 'delay')
transpose_kernel = \
self.config.get('simulation', 'keras_backend') == 'tensorflow'
self._conns, self._biases = build_convolution(layer, delay,
transpose_kernel)
print("layer name {}".format(layer.name))
weights = self._conns
for i, w in enumerate(weights):
if w[2] >= 0:
self._con_exconns.append(w)
else:
self._con_inconns.append(w)
self.set_biases()
#self.connections.append(self.sim.Projection(
# self.layers[-2], self.layers[-1],
# self.sim.FromListConnector(self._conns, ['weight', 'delay'])))
self.proj_excon = self.sim.Projection(self.layers[-2],
self.layers[-1],
self.sim.FromListConnector(
self._con_exconns,
['weight', 'delay']),
receptor_type='excitatory')
self.connections.append(self.proj_excon)
self.proj_incon = self.sim.Projection(self.layers[-2],
self.layers[-1],
self.sim.FromListConnector(
self._con_inconns,
['weight', 'delay']),
receptor_type='inhibitory')
self.connections.append(self.proj_incon)
def build_convolution(self, layer):
# If the parsed model contains a ZeroPadding layer, we need to tell the
# Conv layer about it here, because ZeroPadding layers are removed when
# building the pyNN model.
if self.change_padding:
if layer.padding == 'valid':
self.change_padding = False
layer.padding = 'ZeroPadding'
else:
raise NotImplementedError(
"Border_mode {} in combination with ZeroPadding is not "
"supported.".format(layer.padding))
delay = self.config.getfloat('cell', 'delay')
transpose_kernel = \
self.config.get('simulation', 'keras_backend') == 'tensorflow'
if get_type(layer) in ['Conv2D', 'SparseConv2D']:
weights, biases = build_convolution(layer, delay, transpose_kernel)
elif get_type(layer) in ['DepthwiseConv2D', 'SparseDepthwiseConv2D']:
weights, biases = build_depthwise_convolution(
layer, delay, transpose_kernel)
elif get_type(layer) == 'Conv1D':
weights, biases = build_1d_convolution(layer, delay)
else:
ValueError("Layer {} of type {} unrecognised here. "
"How did you get into this function?".format(
layer.name, get_type(layer)))
self.set_biases(biases)
weights = self.scale_weights(weights)
exc_connections = [c for c in weights if c[2] > 0]
inh_connections = [c for c in weights if c[2] < 0]
if self.config.getboolean('tools', 'simulate'):
self.connections.append(
self.sim.Projection(
self.layers[-2],
self.layers[-1], (self.sim.FromListConnector(
exc_connections, ['weight', 'delay'])),
receptor_type='excitatory',
label=self.layers[-1].label + '_excitatory'))
self.connections.append(
self.sim.Projection(
self.layers[-2],
self.layers[-1], (self.sim.FromListConnector(
inh_connections, ['weight', 'delay'])),
receptor_type='inhibitory',
label=self.layers[-1].label + '_inhibitory'))
else:
# The spinnaker implementation of Projection.save() is not working
# yet, so we do save the connections manually here.
filepath = os.path.join(self.config.get('paths', 'path_wd'),
self.layers[-1].label)
# noinspection PyTypeChecker
np.savetxt(filepath + '_excitatory',
np.array(exc_connections),
['%d', '%d', '%.18f', '%.3f'],
header="columns = ['i', 'j', 'weight', 'delay']")
# noinspection PyTypeChecker
np.savetxt(filepath + '_inhibitory',
np.array(inh_connections),
['%d', '%d', '%.18f', '%.3f'],
header="columns = ['i', 'j', 'weight', 'delay']")