jpthu17 / hbi Goto Github PK

Contributors

Stargazers

Forkers

qiyue0306 whuhxb bupabupa pppeng21

 for i in range(self.t_len):
            for j in range(self.v_len):
                for _ in range(self.num):
                    banzhaf[:, i, j] = self.banzhaf_interaction(retrieve_logits, text_mask, video_mask, text_weight,
                                                                    video_weight, i, j)
        banzhaf = banzhaf / self.num
        banzhaf = torch.einsum('btv,bt->btv', [banzhaf, text_mask])
        banzhaf = torch.einsum('btv,bv->btv', [banzhaf, video_mask])
        return banzhaf

        s_t = (torch.rand((self.t_len)) > 0.5).long().to(retrieve_logits.device) 
        s_j = (torch.rand((self.v_len)) > 0.5).long().to(retrieve_logits.device) 
        s_t[i], s_j[j] = 0, 0

        _text_mask, _video_mask = text_mask.clone(), video_mask.clone()
        _text_mask[:, s_t] = 0
        _video_mask[:, s_j] = 0