def __call__(self, xs):
"""
xs [(w,s,p,y), ..., ]
w: word, c: char, l: length, y: label
"""
batchsize = len(xs)
ws, cs, ls, ts = zip(*xs)
# cs: [(sentence length, max word length)]
ws = map(self.emb_word, ws)
# ls: [(sentence length, char dim)]
# cs = map(lambda (c, l): F.sum(self.emb_char(c), 1) / l, zip(cs, ls))
# cs = [F.reshape(F.average_pooling_2d(
# F.expand_dims(self.emb_char(c), 0), (l, 1)), (-1, self.char_dim))
# for c, l in zip(cs, ls)]
# before conv: (sent len, 1, max word len, char_size)
# after conv: (sent len, char_size, max word len, 1)
# after max_pool: (sent len, char_size, 1, 1)
cs = [F.squeeze(
F.max_pooling_2d(
self.conv_char(
F.expand_dims(
self.emb_char(c), 1)), (l, 1)))
for c, l in zip(cs, ls)]
# [(sentence length, (word_dim + char_dim))]
xs_f = [F.dropout(F.concat([w, c]),
self.dropout_ratio, train=self.train) for w, c in zip(ws, cs)]
xs_b = [x[::-1] for x in xs_f]
cx_f, hx_f, cx_b, hx_b = self._init_state(batchsize)
_, _, hs_f = self.lstm_f(hx_f, cx_f, xs_f, train=self.train)
_, _, hs_b = self.lstm_b(hx_b, cx_b, xs_b, train=self.train)
hs_b = [x[::-1] for x in hs_b]
# ys: [(sentence length, number of category)]
ys = [self.linear2(F.relu(self.linear1(F.concat([h_f, h_b]))))
for h_f, h_b in zip(hs_f, hs_b)]
# ys = [self.linear2(F.relu(
# self.linear1(
# F.squeeze(
# F.transpose(
# F.relu(self.conv1(
# F.reshape(
# F.concat([h_f, h_b]),
# (1, 1, -1, 2 * self.hidden_dim))), (0, 3, 2, 1))
# )))))
# for h_f, h_b in zip(hs_f, hs_b)]
loss = reduce(lambda x, y: x + y,
[F.softmax_cross_entropy(y, t) for y, t in zip(ys, ts)])
acc = reduce(lambda x, y: x + y,
[F.accuracy(y, t, ignore_label=IGNORE) for y, t in zip(ys, ts)])
acc /= batchsize
chainer.report({
"loss": loss,
"accuracy": acc
}, self)
return loss
评论列表
文章目录
