Python Tensor.topk方法代码示例

# 需要导入模块: from torch import Tensor [as 别名]
# 或者: from torch.Tensor import topk [as 别名]
def topk_demo(wl_dist: Tensor, ncubes: int):
    """ torch.topk() only returns the chosen index, sometimes I want to split the tensor,
        i.e., derive the other indices as well.
    """
    batch_dist, topk_idxs = wl_dist.topk(ncubes, sorted=False)  # topk_idxs: size <K>
    other_idxs = torch.arange(len(wl_dist))  # <Batch>
    other_idxs = torch.ones_like(other_idxs).byte().scatter_(-1, topk_idxs, 0)  # topk_idxs are 0, others are 1
    other_idxs = other_idxs.nonzero().squeeze(dim=-1)  # <Batch-K>
    return topk_idxs, other_idxs

# 需要导入模块: from torch import Tensor [as 别名]
# 或者: from torch.Tensor import topk [as 别名]
    def __call__(self,
                 predictions: torch.Tensor,
                 gold_labels: torch.Tensor,
                 mask: Optional[torch.Tensor] = None):
        """
        Parameters
        ----------
        predictions : ``torch.Tensor``, required.
            A tensor of predictions of shape (batch_size, ..., num_classes).
        gold_labels : ``torch.Tensor``, required.
            A tensor of integer class label of shape (batch_size, ...). It must be the same
            shape as the ``predictions`` tensor without the ``num_classes`` dimension.
        mask: ``torch.Tensor``, optional (default = None).
            A masking tensor the same size as ``gold_labels``.
        """
        predictions, gold_labels, mask = self.unwrap_to_tensors(predictions, gold_labels, mask)

        # Some sanity checks.
        num_classes = predictions.size(-1)
        if gold_labels.dim() != predictions.dim() - 1:
            raise ConfigurationError("gold_labels must have dimension == predictions.size() - 1 but "
                                     "found tensor of shape: {}".format(predictions.size()))
        if (gold_labels >= num_classes).any():
            raise ConfigurationError("A gold label passed to Categorical Accuracy contains an id >= {}, "
                                     "the number of classes.".format(num_classes))

        predictions = predictions.view((-1, num_classes))
        gold_labels = gold_labels.view(-1).long()
        if not self._tie_break:
            # Top K indexes of the predictions (or fewer, if there aren't K of them).
            # Special case topk == 1, because it's common and .max() is much faster than .topk().
            if self._top_k == 1:
                top_k = predictions.max(-1)[1].unsqueeze(-1)
            else:
                top_k = predictions.topk(min(self._top_k, predictions.shape[-1]), -1)[1]

            # This is of shape (batch_size, ..., top_k).
            correct = top_k.eq(gold_labels.unsqueeze(-1)).float()
        else:
            # prediction is correct if gold label falls on any of the max scores. distribute score by tie_counts
            max_predictions = predictions.max(-1)[0]
            max_predictions_mask = predictions.eq(max_predictions.unsqueeze(-1))
            # max_predictions_mask is (rows X num_classes) and gold_labels is (batch_size)
            # ith entry in gold_labels points to index (0-num_classes) for ith row in max_predictions
            # For each row check if index pointed by gold_label is was 1 or not (among max scored classes)
            correct = max_predictions_mask[torch.arange(gold_labels.numel()).long(), gold_labels].float()
            tie_counts = max_predictions_mask.sum(-1)
            correct /= tie_counts.float()
            correct.unsqueeze_(-1)

        if mask is not None:
            correct *= mask.view(-1, 1).float()
            self.total_count += mask.sum()
        else:
            self.total_count += gold_labels.numel()
        self.correct_count += correct.sum()

# 需要导入模块: from torch import Tensor [as 别名]
# 或者: from torch.Tensor import topk [as 别名]
    def __call__(self,
                 predictions: torch.Tensor,
                 gold_labels: torch.Tensor,
                 mask: Optional[torch.Tensor] = None):
        """
        Parameters
        ----------
        predictions : ``torch.Tensor``, required.
            A tensor of predictions of shape (batch_size, ..., num_classes).
        gold_labels : ``torch.Tensor``, required.
            A tensor of integer class label of shape (batch_size, ...). It must be the same
            shape as the ``predictions`` tensor without the ``num_classes`` dimension.
        mask: ``torch.Tensor``, optional (default = None).
            A masking tensor the same size as ``gold_labels``.
        """
        # Get the data from the Variables.
        predictions, gold_labels, mask = self.unwrap_to_tensors(predictions, gold_labels, mask)

        # Some sanity checks.
        num_classes = predictions.size(-1)
        if gold_labels.dim() != predictions.dim() - 1:
            raise ConfigurationError("gold_labels must have dimension == predictions.size() - 1 but "
                                     "found tensor of shape: {}".format(predictions.size()))
        if (gold_labels >= num_classes).any():
            raise ConfigurationError("A gold label passed to Categorical Accuracy contains an id >= {}, "
                                     "the number of classes.".format(num_classes))

        # Top K indexes of the predictions (or fewer, if there aren't K of them).
        # Special case topk == 1, because it's common and .max() is much faster than .topk().
        if self._top_k == 1:
            top_k = predictions.max(-1)[1].unsqueeze(-1)
        else:
            top_k = predictions.topk(min(self._top_k, predictions.shape[-1]), -1)[1]

        # This is of shape (batch_size, ..., top_k).
        correct = top_k.eq(gold_labels.long().unsqueeze(-1)).float()

        if mask is not None:
            correct *= mask.float().unsqueeze(-1)
            self.total_count += mask.sum()
        else:
            self.total_count += gold_labels.numel()
        self.correct_count += correct.sum()