def forward(self, x, train=True, mask=None, use_batchwise_mask=True):
"""Applies the simplified dropconnect layer.
Args:
x (chainer.Variable or :ref:`ndarray`):
Batch of input vectors. Its first dimension ``n`` is assumed
to be the *minibatch dimension*.
train (bool):
If ``True``, executes simplified dropconnect.
Otherwise, simplified dropconnect link works as a linear unit.
mask (None or chainer.Variable or :ref:`ndarray`):
If ``None``, randomized simplified dropconnect mask is
generated. Otherwise, The mask must be ``(n, M, N)`` or
``(M, N)`` shaped array, and `use_batchwise_mask` is ignored.
Main purpose of this option is debugging.
`mask` array will be used as a dropconnect mask.
use_batchwise_mask (bool):
If ``True``, dropped connections depend on each sample in
mini-batch.
Returns:
~chainer.Variable: Output of the simplified dropconnect layer.
"""
if self.W.array is None:
self._initialize_params(x.size // len(x))
if mask is not None and 'mask' not in self.__dict__:
self.add_persistent('mask', mask)
return simplified_dropconnect.simplified_dropconnect(
x, self.W, self.b, self.ratio, train, mask, use_batchwise_mask)
def __call__(self, x, train=True, mask=None):
"""Applies the simplified dropconnect layer.
Args:
x (chainer.Variable or :class:`numpy.ndarray` or cupy.ndarray):
Batch of input vectors. Its first dimension ``n`` is assumed
to be the *minibatch dimension*.
train (bool):
If ``True``, executes simplified dropconnect.
Otherwise, simplified dropconnect link works as a linear unit.
mask (None or chainer.Variable or numpy.ndarray or cupy.ndarray):
If ``None``, randomized simplified dropconnect mask is
generated. Otherwise, The mask must be ``(n, M, N)``
shaped array. Main purpose of this option is debugging.
`mask` array will be used as a dropconnect mask.
Returns:
~chainer.Variable: Output of the simplified dropconnect layer.
"""
if self.W.data is None:
self._initialize_params(x.size // len(x.data))
if mask is not None and 'mask' not in self.__dict__:
self.add_persistent('mask', mask)
return simplified_dropconnect.simplified_dropconnect(
x, self.W, self.b, self.ratio, train, mask)
def __call__(self, x, train=True, mask=None):
"""Applies the simplified dropconnect layer.
Args:
x (chainer.Variable or :class:`numpy.ndarray` or cupy.ndarray):
Batch of input vectors. Its first dimension ``n`` is assumed
to be the *minibatch dimension*.
train (bool):
If ``True``, executes simplified dropconnect.
Otherwise, simplified dropconnect link works as a linear unit.
mask (None or chainer.Variable or numpy.ndarray or cupy.ndarray):
If ``None``, randomized simplified dropconnect mask is
generated. Otherwise, The mask must be ``(n, M, N)``
shaped array. Main purpose of this option is debugging.
`mask` array will be used as a dropconnect mask.
Returns:
~chainer.Variable: Output of the simplified dropconnect layer.
"""
if self.W.data is None:
self._initialize_params(x.size // len(x.data))
if mask is not None and 'mask' not in self.__dict__:
self.add_persistent('mask', mask)
return simplified_dropconnect.simplified_dropconnect(x, self.W, self.b,
self.ratio, train,
mask)