lstm.py 文件源码

def solve(self, x_seq, pos, neg, train=True, variablize=False, onebyone=True):
        if variablize:# If arguments are just arrays (not variables), make them variables
            x_seq = [chainer.Variable(x, volatile=not train) for x in x_seq]
            x_seq = [F.dropout(x, ratio=self.dropout_ratio, train=train) for x in x_seq]
            pos = self.act1(self.W_candidate(
                F.dropout(chainer.Variable(pos, volatile=not train),
                          ratio=self.dropout_ratio, train=train)))
            neg = self.act1(self.W_candidate(
                F.dropout(chainer.Variable(neg, volatile=not train),
                          ratio=self.dropout_ratio, train=train)))
        if onebyone and train:
            target_x_seq = [self.act1(self.W_candidate(x)) for x in x_seq[:4]]# 1,2,3,4,5-th targets
            onebyone_loss = 0.

        self.LSTM.reset_state()
        for i, x in enumerate(x_seq):
            h = self.LSTM( F.dropout(x, ratio=self.dropout_ratio, train=train) )
            if onebyone and train and target_x_seq[i+1:]:
                pos_score, neg_score = self.calculate_score(h, target_x_seq[i+1:], neg,
                                                            multipos=True)
                onebyone_loss += F.relu( self.margin - pos_score + neg_score )

        pos_score, neg_score = self.calculate_score(h, pos, neg)
        accum_loss = F.relu( self.margin - pos_score + neg_score )
        TorFs = sum(accum_loss.data < self.margin)

        if onebyone and train:
            return F.sum(accum_loss) + F.sum(onebyone_loss), TorFs
        else:
            return F.sum(accum_loss), TorFs