pytorch_transformers/modeling_utils.py [758:809]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - if start_positions is not None and end_positions is not None: # If we are on multi-GPU, let's remove the dimension added by batch splitting for x in (start_positions, end_positions, cls_index, is_impossible): if x is not None and x.dim() > 1: x.squeeze_(-1) # during training, compute the end logits based on the ground truth of the start position end_logits = self.end_logits(hidden_states, start_positions=start_positions, p_mask=p_mask) loss_fct = CrossEntropyLoss() start_loss = loss_fct(start_logits, start_positions) end_loss = loss_fct(end_logits, end_positions) total_loss = (start_loss + end_loss) / 2 if cls_index is not None and is_impossible is not None: # Predict answerability from the representation of CLS and START cls_logits = self.answer_class(hidden_states, start_positions=start_positions, cls_index=cls_index) loss_fct_cls = nn.BCEWithLogitsLoss() cls_loss = loss_fct_cls(cls_logits, is_impossible) # note(zhiliny): by default multiply the loss by 0.5 so that the scale is comparable to start_loss and end_loss total_loss += cls_loss * 0.5 outputs = (total_loss,) + outputs else: # during inference, compute the end logits based on beam search bsz, slen, hsz = hidden_states.size() start_log_probs = F.softmax(start_logits, dim=-1) # shape (bsz, slen) start_top_log_probs, start_top_index = torch.topk(start_log_probs, self.start_n_top, dim=-1) # shape (bsz, start_n_top) start_top_index_exp = start_top_index.unsqueeze(-1).expand(-1, -1, hsz) # shape (bsz, start_n_top, hsz) start_states = torch.gather(hidden_states, -2, start_top_index_exp) # shape (bsz, start_n_top, hsz) start_states = start_states.unsqueeze(1).expand(-1, slen, -1, -1) # shape (bsz, slen, start_n_top, hsz) hidden_states_expanded = hidden_states.unsqueeze(2).expand_as(start_states) # shape (bsz, slen, start_n_top, hsz) p_mask = p_mask.unsqueeze(-1) if p_mask is not None else None end_logits = self.end_logits(hidden_states_expanded, start_states=start_states, p_mask=p_mask) end_log_probs = F.softmax(end_logits, dim=1) # shape (bsz, slen, start_n_top) end_top_log_probs, end_top_index = torch.topk(end_log_probs, self.end_n_top, dim=1) # shape (bsz, end_n_top, start_n_top) end_top_log_probs = end_top_log_probs.view(-1, self.start_n_top * self.end_n_top) end_top_index = end_top_index.view(-1, self.start_n_top * self.end_n_top) start_states = torch.einsum("blh,bl->bh", hidden_states, start_log_probs) cls_logits = self.answer_class(hidden_states, start_states=start_states, cls_index=cls_index) outputs = (start_top_log_probs, start_top_index, end_top_log_probs, end_top_index, cls_logits) + outputs # return start_top_log_probs, start_top_index, end_top_log_probs, end_top_index, cls_logits # or (if labels are provided) (total_loss,) return outputs - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - pytorch_transformers/modeling_xlnet.py [1244:1295]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - if start_positions is not None and end_positions is not None: # If we are on multi-GPU, let's remove the dimension added by batch splitting for x in (start_positions, end_positions, cls_index, is_impossible): if x is not None and x.dim() > 1: x.squeeze_(-1) # during training, compute the end logits based on the ground truth of the start position end_logits = self.end_logits(hidden_states, start_positions=start_positions, p_mask=p_mask) loss_fct = CrossEntropyLoss() start_loss = loss_fct(start_logits, start_positions) end_loss = loss_fct(end_logits, end_positions) total_loss = (start_loss + end_loss) / 2 if cls_index is not None and is_impossible is not None: # Predict answerability from the representation of CLS and START cls_logits = self.answer_class(hidden_states, start_positions=start_positions, cls_index=cls_index) loss_fct_cls = nn.BCEWithLogitsLoss() cls_loss = loss_fct_cls(cls_logits, is_impossible) # note(zhiliny): by default multiply the loss by 0.5 so that the scale is comparable to start_loss and end_loss total_loss += cls_loss * 0.5 outputs = (total_loss,) + outputs else: # during inference, compute the end logits based on beam search bsz, slen, hsz = hidden_states.size() start_log_probs = F.softmax(start_logits, dim=-1) # shape (bsz, slen) start_top_log_probs, start_top_index = torch.topk(start_log_probs, self.start_n_top, dim=-1) # shape (bsz, start_n_top) start_top_index_exp = start_top_index.unsqueeze(-1).expand(-1, -1, hsz) # shape (bsz, start_n_top, hsz) start_states = torch.gather(hidden_states, -2, start_top_index_exp) # shape (bsz, start_n_top, hsz) start_states = start_states.unsqueeze(1).expand(-1, slen, -1, -1) # shape (bsz, slen, start_n_top, hsz) hidden_states_expanded = hidden_states.unsqueeze(2).expand_as(start_states) # shape (bsz, slen, start_n_top, hsz) p_mask = p_mask.unsqueeze(-1) if p_mask is not None else None end_logits = self.end_logits(hidden_states_expanded, start_states=start_states, p_mask=p_mask) end_log_probs = F.softmax(end_logits, dim=1) # shape (bsz, slen, start_n_top) end_top_log_probs, end_top_index = torch.topk(end_log_probs, self.end_n_top, dim=1) # shape (bsz, end_n_top, start_n_top) end_top_log_probs = end_top_log_probs.view(-1, self.start_n_top * self.end_n_top) end_top_index = end_top_index.view(-1, self.start_n_top * self.end_n_top) start_states = torch.einsum("blh,bl->bh", hidden_states, start_log_probs) # get the representation of START as weighted sum of hidden states cls_logits = self.answer_class(hidden_states, start_states=start_states, cls_index=cls_index) # Shape (batch size,): one single `cls_logits` for each sample outputs = (start_top_log_probs, start_top_index, end_top_log_probs, end_top_index, cls_logits) + outputs # return start_top_log_probs, start_top_index, end_top_log_probs, end_top_index, cls_logits # or (if labels are provided) (total_loss,) return outputs - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -