def __call__(self, hx, cx, xs):
"""Calculate all hidden states and cell states.
Args:
hx (~chainer.Variable): Initial hidden states.
cx (~chainer.Variable): Initial cell states.
xs (list of ~chianer.Variable): List of input sequences.
Each element ``xs[i]`` is a :class:`chainer.Variable` holding
a sequence.
"""
assert isinstance(xs, (list, tuple))
indices = argsort_list_descent(xs)
xs = permutate_list(xs, indices, inv=False)
hx = permutate.permutate(hx, indices, axis=1, inv=False)
cx = permutate.permutate(cx, indices, axis=1, inv=False)
trans_x = transpose_sequence.transpose_sequence(xs)
ws = [[w.w0, w.w1, w.w2, w.w3, w.w4, w.w5, w.w6, w.w7] for w in self]
bs = [[w.b0, w.b1, w.b2, w.b3, w.b4, w.b5, w.b6, w.b7] for w in self]
hy, cy, trans_y = rnn.n_step_lstm(
self.n_layers, self.dropout, hx, cx, ws, bs, trans_x,
use_cudnn=self.use_cudnn)
hy = permutate.permutate(hy, indices, axis=1, inv=True)
cy = permutate.permutate(cy, indices, axis=1, inv=True)
ys = transpose_sequence.transpose_sequence(trans_y)
ys = permutate_list(ys, indices, inv=True)
return hy, cy, ys
def _call(self, hs, xs, **kwargs):
if kwargs:
argument.check_unexpected_kwargs(
kwargs,
train="train argument is not supported anymore. "
"Use chainer.using_config",
)
argument.assert_kwargs_empty(kwargs)
assert isinstance(xs, (list, tuple))
indices = argsort_list_descent(xs)
assert self.ws[0][0].shape[1] == xs[0].shape[1] # input check
xs = permutate_list(xs, indices, inv=False)
hxs = []
for hx in hs:
if hx is None:
hx = self.init_hx(xs)
else:
hx = permutate.permutate(hx, indices, axis=1, inv=False)
hxs.append(hx)
trans_x = transpose_sequence.transpose_sequence(xs)
args = [self.n_layers, self.dropout] + hxs + [self.ws, self.bs, trans_x]
result = self.rnn(*args)
hys = [permutate.permutate(h, indices, axis=1, inv=True) for h in result[:-1]]
trans_y = result[-1]
ys = transpose_sequence.transpose_sequence(trans_y)
ys = permutate_list(ys, indices, inv=True)
return hys, ys
def __call__(self, hx, cx, xs, train=True):
"""Calculate all hidden states and cell states.
Args:
hx (~chainer.Variable): Initial hidden states.
cx (~chainer.Variable): Initial cell states.
xs (list of ~chianer.Variable): List of input sequences.
Each element ``xs[i]`` is a :class:`chainer.Variable` holding
a sequence.
"""
assert isinstance(xs, (list, tuple))
indices = argsort_list_descent(xs)
xs = permutate_list(xs, indices, inv=False)
hx = permutate.permutate(hx, indices, axis=1, inv=False)
cx = permutate.permutate(cx, indices, axis=1, inv=False)
trans_x = transpose_sequence.transpose_sequence(xs)
ws = [[w.w0, w.w1, w.w2, w.w3, w.w4, w.w5, w.w6, w.w7] for w in self]
bs = [[w.b0, w.b1, w.b2, w.b3, w.b4, w.b5, w.b6, w.b7] for w in self]
hy, cy, trans_y = rnn.n_step_lstm(
self.n_layers, self.dropout, hx, cx, ws, bs, trans_x,
train=train, use_cudnn=self.use_cudnn)
hy = permutate.permutate(hy, indices, axis=1, inv=True)
cy = permutate.permutate(cy, indices, axis=1, inv=True)
ys = transpose_sequence.transpose_sequence(trans_y)
ys = permutate_list(ys, indices, inv=True)
return hy, cy, ys
def __call__(self, hx, xs, train=True):
"""Calculate all hidden states and cell states.
Args:
hx (~chainer.Variable or None): Initial hidden states. If ``None``
is specified zero-vector is used.
xs (list of ~chianer.Variable): List of input sequences.
Each element ``xs[i]`` is a :class:`chainer.Variable` holding
a sequence.
"""
assert isinstance(xs, (list, tuple))
indices = argsort_list_descent(xs)
xs = permutate_list(xs, indices, inv=False)
if hx is None:
hx = self.init_hx(xs)
else:
hx = permutate.permutate(hx, indices, axis=1, inv=False)
trans_x = transpose_sequence.transpose_sequence(xs)
ws = [[w.w0, w.w1] for w in self]
bs = [[w.b0, w.b1] for w in self]
hy, trans_y = self.rnn(
self.n_layers, self.dropout, hx, ws, bs, trans_x,
train=train, use_cudnn=self.use_cudnn, activation=self.activation)
hy = permutate.permutate(hy, indices, axis=1, inv=True)
ys = transpose_sequence.transpose_sequence(trans_y)
ys = permutate_list(ys, indices, inv=True)
return hy, ys
def __call__(self, hx, cx, xs, **kwargs):
"""__call__(self, hx, cx, xs)
Calculate all hidden states and cell states.
.. warning::
``train`` argument is not supported anymore since v2.
Instead, use ``chainer.using_config('train', train)``.
See :func:`chainer.using_config`.
Args:
hx (~chainer.Variable or None): Initial hidden states. If ``None``
is specified zero-vector is used.
cx (~chainer.Variable or None): Initial cell states. If ``None``
is specified zero-vector is used.
xs (list of ~chainer.Variable): List of input sequences.
Each element ``xs[i]`` is a :class:`chainer.Variable` holding
a sequence.
"""
argument.check_unexpected_kwargs(
kwargs,
train='train argument is not supported anymore. '
'Use chainer.using_config')
argument.assert_kwargs_empty(kwargs)
assert isinstance(xs, (list, tuple))
xp = cuda.get_array_module(hx, *xs)
indices = n_step_rnn.argsort_list_descent(xs)
indices_array = xp.array(indices)
xs = n_step_rnn.permutate_list(xs, indices, inv=False)
if hx is None:
hx = self.init_hx(xs)
else:
hx = permutate.permutate(hx, indices_array, axis=1, inv=False)
if cx is None:
cx = self.init_hx(xs)
else:
cx = permutate.permutate(cx, indices_array, axis=1, inv=False)
trans_x = transpose_sequence.transpose_sequence(xs)
ws = [[w.w0, w.w1, w.w2, w.w3, w.w4, w.w5, w.w6, w.w7] for w in self]
bs = [[w.b0, w.b1, w.b2, w.b3, w.b4, w.b5, w.b6, w.b7] for w in self]
hy, cy, trans_y = self.rnn(self.n_layers, self.dropout, hx, cx, ws, bs,
trans_x)
hy = permutate.permutate(hy, indices_array, axis=1, inv=True)
cy = permutate.permutate(cy, indices_array, axis=1, inv=True)
ys = transpose_sequence.transpose_sequence(trans_y)
ys = n_step_rnn.permutate_list(ys, indices, inv=True)
return hy, cy, ys
def __call__(self, hx, cx, xs, train=True):
"""Calculate all hidden states and cell states.
Args:
hx (~chainer.Variable or None): Initial hidden states. If ``None``
is specified zero-vector is used.
cx (~chainer.Variable or None): Initial cell states. If ``None``
is specified zero-vector is used.
xs (list of ~chianer.Variable): List of input sequences.
Each element ``xs[i]`` is a :class:`chainer.Variable` holding
a sequence.
"""
assert isinstance(xs, (list, tuple))
indices = argsort_list_descent(xs)
xs = permutate_list(xs, indices, inv=False)
if hx is None:
with cuda.get_device(self._device_id):
hx = chainer.Variable(self.xp.zeros(
(self.n_layers, len(xs), self.out_size),
dtype=xs[0].dtype),
volatile='auto')
else:
hx = permutate.permutate(hx, indices, axis=1, inv=False)
if cx is None:
with cuda.get_device(self._device_id):
cx = chainer.Variable(self.xp.zeros(
(self.n_layers, len(xs), self.out_size),
dtype=xs[0].dtype),
volatile='auto')
else:
cx = permutate.permutate(cx, indices, axis=1, inv=False)
trans_x = transpose_sequence.transpose_sequence(xs)
ws = [[w.w0, w.w1, w.w2, w.w3, w.w4, w.w5, w.w6, w.w7] for w in self]
bs = [[w.b0, w.b1, w.b2, w.b3, w.b4, w.b5, w.b6, w.b7] for w in self]
hy, cy, trans_y = rnn.n_step_lstm(self.n_layers,
self.dropout,
hx,
cx,
ws,
bs,
trans_x,
train=train,
use_cudnn=self.use_cudnn)
hy = permutate.permutate(hy, indices, axis=1, inv=True)
cy = permutate.permutate(cy, indices, axis=1, inv=True)
ys = transpose_sequence.transpose_sequence(trans_y)
ys = permutate_list(ys, indices, inv=True)
return hy, cy, ys
def __call__(self, hx, cx, xs, **kwargs):
"""__call__(self, hx, cx, xs)
Calculate all hidden states and cell states.
.. warning::
``train`` argument is not supported anymore since v2.
Instead, use ``chainer.using_config('train', train)``.
See :func:`chainer.using_config`.
Args:
hx (~chainer.Variable or None): Initial hidden states. If ``None``
is specified zero-vector is used.
cx (~chainer.Variable or None): Initial cell states. If ``None``
is specified zero-vector is used.
xs (list of ~chianer.Variable): List of input sequences.
Each element ``xs[i]`` is a :class:`chainer.Variable` holding
a sequence.
"""
argument.check_unexpected_kwargs(
kwargs, train='train argument is not supported anymore. '
'Use chainer.using_config')
argument.assert_kwargs_empty(kwargs)
assert isinstance(xs, (list, tuple))
indices = n_step_rnn.argsort_list_descent(xs)
xs = n_step_rnn.permutate_list(xs, indices, inv=False)
if hx is None:
hx = self.init_hx(xs)
else:
hx = permutate.permutate(hx, indices, axis=1, inv=False)
if cx is None:
cx = self.init_hx(xs)
else:
cx = permutate.permutate(cx, indices, axis=1, inv=False)
trans_x = transpose_sequence.transpose_sequence(xs)
ws = [[w.w0, w.w1, w.w2, w.w3, w.w4, w.w5, w.w6, w.w7] for w in self]
bs = [[w.b0, w.b1, w.b2, w.b3, w.b4, w.b5, w.b6, w.b7] for w in self]
hy, cy, trans_y = self.rnn(
self.n_layers, self.dropout, hx, cx, ws, bs, trans_x)
hy = permutate.permutate(hy, indices, axis=1, inv=True)
cy = permutate.permutate(cy, indices, axis=1, inv=True)
ys = transpose_sequence.transpose_sequence(trans_y)
ys = n_step_rnn.permutate_list(ys, indices, inv=True)
return hy, cy, ys
def __call__(self, hx, cx, xs, train=True):
"""Calculate all hidden states and cell states.
Args:
hx (~chainer.Variable or None): Initial hidden states. If ``None``
is specified zero-vector is used.
cx (~chainer.Variable or None): Initial cell states. If ``None``
is specified zero-vector is used.
xs (list of ~chianer.Variable): List of input sequences.
Each element ``xs[i]`` is a :class:`chainer.Variable` holding
a sequence.
"""
assert isinstance(xs, (list, tuple))
indices = argsort_list_descent(xs)
xs = permutate_list(xs, indices, inv=False)
if hx is None:
with cuda.get_device(self._device_id):
hx = chainer.Variable(
self.xp.zeros(
(self.n_layers, len(xs), self.out_size),
dtype=xs[0].dtype),
volatile='auto')
else:
hx = permutate.permutate(hx, indices, axis=1, inv=False)
if cx is None:
with cuda.get_device(self._device_id):
cx = chainer.Variable(
self.xp.zeros(
(self.n_layers, len(xs), self.out_size),
dtype=xs[0].dtype),
volatile='auto')
else:
cx = permutate.permutate(cx, indices, axis=1, inv=False)
trans_x = transpose_sequence.transpose_sequence(xs)
ws = [[w.w0, w.w1, w.w2, w.w3, w.w4, w.w5, w.w6, w.w7] for w in self]
bs = [[w.b0, w.b1, w.b2, w.b3, w.b4, w.b5, w.b6, w.b7] for w in self]
hy, cy, trans_y = rnn.n_step_lstm(
self.n_layers, self.dropout, hx, cx, ws, bs, trans_x,
train=train, use_cudnn=self.use_cudnn)
hy = permutate.permutate(hy, indices, axis=1, inv=True)
cy = permutate.permutate(cy, indices, axis=1, inv=True)
ys = transpose_sequence.transpose_sequence(trans_y)
ys = permutate_list(ys, indices, inv=True)
return hy, cy, ys
def _call(self, hs, xs, **kwargs):
"""Calls RNN function.
Args:
hs (list of ~chainer.Variable or None): Lisit of hidden states.
Its length depends on its implementation.
If ``None`` is specified zero-vector is used.
xs (list of ~chainer.Variable): List of input sequences.
Each element ``xs[i]`` is a :class:`chainer.Variable` holding
a sequence.
Returns:
tuple: hs
"""
if kwargs:
argument.check_unexpected_kwargs(
kwargs,
train='train argument is not supported anymore. '
'Use chainer.using_config')
argument.assert_kwargs_empty(kwargs)
assert isinstance(xs, (list, tuple))
xp = cuda.get_array_module(*(list(hs) + list(xs)))
indices = argsort_list_descent(xs)
indices_array = xp.array(indices)
xs = permutate_list(xs, indices, inv=False)
hxs = []
for hx in hs:
if hx is None:
hx = self.init_hx(xs)
else:
hx = permutate.permutate(hx, indices_array, axis=1, inv=False)
hxs.append(hx)
trans_x = transpose_sequence.transpose_sequence(xs)
args = [self.n_layers, self.dropout] + hxs + \
[self.ws, self.bs, trans_x]
result = self.rnn(*args)
hys = [
permutate.permutate(h, indices_array, axis=1, inv=True)
for h in result[:-1]
]
trans_y = result[-1]
ys = transpose_sequence.transpose_sequence(trans_y)
ys = permutate_list(ys, indices, inv=True)
return hys, ys
def _call(self, hs, xs, **kwargs):
"""Calls RNN function.
Args:
hs (list of ~chainer.Variable or None): Lisit of hidden states.
Its length depends on its implementation.
If ``None`` is specified zero-vector is used.
xs (list of ~chainer.Variable): List of input sequences.
Each element ``xs[i]`` is a :class:`chainer.Variable` holding
a sequence.
Returns:
tuple: hs
"""
if kwargs:
argument.check_unexpected_kwargs(
kwargs, train='train argument is not supported anymore. '
'Use chainer.using_config')
argument.assert_kwargs_empty(kwargs)
assert isinstance(xs, (list, tuple))
xp = cuda.get_array_module(*(list(hs) + list(xs)))
indices = argsort_list_descent(xs)
indices_array = xp.array(indices)
xs = permutate_list(xs, indices, inv=False)
hxs = []
for hx in hs:
if hx is None:
hx = self.init_hx(xs)
else:
hx = permutate.permutate(hx, indices_array, axis=1, inv=False)
hxs.append(hx)
trans_x = transpose_sequence.transpose_sequence(xs)
args = [self.n_layers, self.dropout] + hxs + \
[self.ws, self.bs, trans_x]
result = self.rnn(*args)
hys = [permutate.permutate(h, indices_array, axis=1, inv=True)
for h in result[:-1]]
trans_y = result[-1]
ys = transpose_sequence.transpose_sequence(trans_y)
ys = permutate_list(ys, indices, inv=True)
return hys, ys
def __call__(self, h0, hx, xs, **kwargs):
"""__call__(self, hx, xs)
Calculate all hidden states and cell states.
.. warning::
``train`` argument is not supported anymore since v2.
Instead, use ``chainer.using_config('train', train)``.
See :func:`chainer.using_config`.
Args:
hx (~chainer.Variable or None): Initial hidden states. If ``None``
is specified zero-vector is used.
xs (list of ~chianer.Variable): List of input sequences.
Each element ``xs[i]`` is a :class:`chainer.Variable` holding
a sequence.
"""
argument.check_unexpected_kwargs(
kwargs,
train='train argument is not supported anymore. '
'Use chainer.using_config')
argument.assert_kwargs_empty(kwargs)
assert isinstance(
xs, (list, tuple)), "xs in not a list or tupple: %r" % type(xs)
indices = argsort_list_descent(xs)
xs = permutate_list(xs, indices, inv=False)
if h0 is None:
h0 = self.init_hx(xs)
else:
h0 = permutate.permutate(h0, indices, axis=1, inv=False)
hx = permutate_list(hx, indices, inv=False)
trans_x = transpose_sequence.transpose_sequence(xs)
ws = [[w.w0, w.w1, w.w2, w.w3, w.w4, w.w5] for w in self]
bs = [[w.b0, w.b1, w.b2, w.b3, w.b4, w.b5] for w in self]
for w in self:
w1 = w.w6
w2 = w.w7
w3 = w.w8
b1 = w.b6
b2 = w.b7
b3 = w.b8
W = [w1, w2, w3]
B = [b1, b2, b3]
h_list, h_bar_list, c_s_list, z_s_list = self.rnn(
self.n_layers, self.dropout, h0, hx, ws, bs, trans_x, W, B)
'''
print(type(h_list),len(h_list))
print(type(h_list[0]),len(h_list[0]))
print(type(h_list[0][0]),len(h_list[0][0]))
'''
#batch内で入れ替え
h_list = transpose_sequence.transpose_sequence(h_list)
h_list = permutate_list(h_list, indices, inv=True)
'''
print(type(h_list),len(h_list))
print(type(h_list[0]),len(h_list[0]))
print(type(h_list[0][0]),len(h_list[0][0]))
'''
h_bar_list = transpose_sequence.transpose_sequence(h_bar_list)
h_bar_list = permutate_list(h_bar_list, indices, inv=True)
'''
print(type(c_s_list),len(c_s_list))
print(type(c_s_list[0]),len(c_s_list[0]))
print(type(c_s_list[0][0]),len(c_s_list[0][0]), c_s_list[0][0])
print(type(z_s_list), len(z_s_list))
print(type(z_s_list[0]), len(z_s_list[0]), z_s_list[0])
'''
c_s_list = transpose_sequence.transpose_sequence(c_s_list)
c_s_list = permutate_list(c_s_list, indices, inv=True)
z_s_list = transpose_sequence.transpose_sequence(z_s_list)
z_s_list = permutate_list(z_s_list, indices, inv=True)
return h_list, h_bar_list, c_s_list, z_s_list
