def seq_rnn_embed(exs, birnn, init_state=None, return_sequences: bool = False):
"""Embed given sequences using rnn."""
# exs.shape == (..., S, E)
seqs = F.reshape(exs, (-1, ) + exs.shape[-2:]) # (X, S, E)
toembed = F.separate(seqs, 0) # X x [(S1, E), (S2, E), ...]
hs, ys = birnn(init_state,
toembed) # (2, X, E), X x [(S1, 2*E), (S2, 2*E), ...]
if return_sequences:
ys = F.stack(ys) # (X, S, 2*E)
ys = F.reshape(ys, exs.shape[:-1] + (-1, )) # (..., S, 2*E)
return ys
hs = F.moveaxis(hs, 0, -2) # (X, 2, E)
hs = F.reshape(hs, exs.shape[:-2] + (-1, )) # (..., 2*E)
return hs
def differentiate(self, x, enable_double_backprop):
"""Calculate derivative of the output data w.r.t. input data.
Args:
x (~chainer.Variable):
Input data which has the shape ``(n_sample, n_input)``.
enable_double_backprop (bool):
Passed to :func:`chainer.grad` to determine whether to
create more deep calculation graph or not.
"""
dy = [chainer.grad([output_node], [x],
enable_double_backprop=enable_double_backprop)[0]
for output_node in F.moveaxis(self.results['y'], 0, -1)]
dy = F.stack(dy, axis=1)
self.results['dy'] = dy
def wsd_with_tc(self, sent, trf_encoded_matrix, labels):
### WSD ###
if self.model_type == "TRF-Multi" or self.model_type == "TRF-Delay-Multi":
y_wsd = self.wsd_only(trf_encoded_matrix, labels)
elif self.model_type == "TRF-Sequential":
y_wsd, task_type = self.wsd_model(sent, None, None,
True) ## 読み込みsequential
y_wsd_soft = F.softmax(y_wsd) ## 予測結果にSoftmaxをかける
argmax_wsd = F.argmax(y_wsd_soft, axis=1) ## 最大のインデクス値を取ってくる
cond = chainer.Variable(
self.xp.array([
True if i != "<PAD>" else False for i in list(chain(*labels))
])) ## 語義のラベルがついていない単語は無視するための条件
pad_array = chainer.Variable(
-1 * self.xp.ones(argmax_wsd.shape, dtype=argmax_wsd.dtype))
pad_array_argmax_wsd = F.where(cond, argmax_wsd, pad_array)
sense_label_embed = F.embed_id(x=pad_array_argmax_wsd,
W=self.xp.array(
self.lookup_table_sense_fixed),
ignore_label=-1) ## 固定.
sense_label_embed = sense_label_embed.reshape(
trf_encoded_matrix.shape[0], trf_encoded_matrix.shape[-1], -1)
origin_shape = sense_label_embed.shape
sense_label_embed = F.moveaxis(sense_label_embed, 1, 2)
## 置き換え ##
cond_reshape = cond.reshape(cond.shape[0], -1)
cond_reshape = F.broadcast_to(
cond_reshape, (cond_reshape.shape[0], trf_encoded_matrix.shape[1]))
cond_reshape = cond_reshape.reshape(origin_shape)
cond_reshape = F.swapaxes(cond_reshape, 1, 2)
replaced_trf_matrix = F.where(cond_reshape, sense_label_embed,
trf_encoded_matrix)
### WSDの予測をTCに組み入れる ###
tc = replaced_trf_matrix ## 置換後の文書行列
### TC ###
tc_features = F.sum(tc, axis=2) ## TC特徴
y_tc = self.fc2(tc_features) ### TCの予測結果
return (y_tc, y_wsd) if (self.model_type == "TRF-Multi") or (
self.model_type == "TRF-Delay-Multi") else y_tc
def forward(self, inputs, device):
x, = inputs
y = functions.moveaxis(x, self.source, self.destination)
return y,
def check_type_error(self, x):
with self.assertRaises(TypeError):
functions.moveaxis(x, self.source, self.destination)
def check_type_error(self, x):
with self.assertRaises(type_check.InvalidType):
functions.moveaxis(x, self.source, self.destination)
def epahser_n_sixaevom(_T_T, flags, dims):
permutation = flatten([[flag.nonzero()[0].tolist()] for flag in flags])
T_T = F.reshape(_T_T, dims + [1] * (max(permutation) - len(dims) + 1))
return F.moveaxis(T_T, range(len(permutation)), permutation)
def moveaxis_n_reshape(T, flags):
permutation = flatten([[flag.nonzero()[0].tolist()] for flag in flags])
T_T = F.moveaxis(T, permutation, range(len(permutation)))
new_shape = [merged_dim(T.shape, flag) for flag in flags]
return F.reshape(T_T, new_shape)
def check_type_error(self, x):
with self.assertRaises(type_check.InvalidType):
functions.moveaxis(x, self.source, self.destination)
def f(x):
y = functions.moveaxis(x, self.source, self.destination)
return y * y
def check_forward(self, x_data):
x = chainer.Variable(x_data)
y = functions.moveaxis(x, self.source, self.destination)
expect = numpy.moveaxis(self.x, self.source, self.destination)
testing.assert_allclose(y.data, expect)
def check_type_error(self, x):
with self.assertRaises(ValueError):
functions.moveaxis(x, self.source, self.destination)
def f(x):
return functions.moveaxis(x, self.source, self.destination)
def check_forward(self, x_data):
x = chainer.Variable(x_data)
y = functions.moveaxis(x, self.source, self.destination)
expect = _moveaxis(self.x, self.source, self.destination)
testing.assert_allclose(y.data, expect)
def forward(self, inputs, device):
x, = inputs
y = functions.moveaxis(x, self.source, self.destination)
return y,