OldModel.py 文件源码

def forward(self, fc_feats, att_feats, seq):
        batch_size = fc_feats.size(0)
        state = self.init_hidden(fc_feats)

        outputs = []

        for i in range(seq.size(1) - 1):
            if self.training and i >= 1 and self.ss_prob > 0.0: # otherwiste no need to sample
                sample_prob = fc_feats.data.new(batch_size).uniform_(0, 1)
                sample_mask = sample_prob < self.ss_prob
                if sample_mask.sum() == 0:
                    it = seq[:, i].clone()
                else:
                    sample_ind = sample_mask.nonzero().view(-1)
                    it = seq[:, i].data.clone()
                    #prob_prev = torch.exp(outputs[-1].data.index_select(0, sample_ind)) # fetch prev distribution: shape Nx(M+1)
                    #it.index_copy_(0, sample_ind, torch.multinomial(prob_prev, 1).view(-1))
                    prob_prev = torch.exp(outputs[-1].data) # fetch prev distribution: shape Nx(M+1)
                    it.index_copy_(0, sample_ind, torch.multinomial(prob_prev, 1).view(-1).index_select(0, sample_ind))
                    it = Variable(it, requires_grad=False)
            else:
                it = seq[:, i].clone()          
            # break if all the sequences end
            if i >= 1 and seq[:, i].data.sum() == 0:
                break

            xt = self.embed(it)

            output, state = self.core(xt, fc_feats, att_feats, state)
            output = F.log_softmax(self.logit(self.dropout(output)))
            outputs.append(output)

        return torch.cat([_.unsqueeze(1) for _ in outputs], 1)