FCModel.py 文件源码

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

        for i in range(seq.size(1)):
            if i == 0:
                xt = self.img_embed(fc_feats)
            else:
                if self.training and i >= 2 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-1].clone()
                    else:
                        sample_ind = sample_mask.nonzero().view(-1)
                        it = seq[:, i-1].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-1].clone()
                # break if all the sequences end
                if i >= 2 and seq[:, i-1].data.sum() == 0:
                    break
                xt = self.embed(it)

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

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