Python torch.Tensor() Examples

def grid_anchors(self, featmap_sizes, device='cuda'):
        """Generate grid anchors in multiple feature levels.

        Args:
            featmap_sizes (list[tuple]): List of feature map sizes in
                multiple feature levels.
            device (str): Device where the anchors will be put on.

        Return:
            list[torch.Tensor]: Anchors in multiple feature levels.
                The sizes of each tensor should be [N, 4], where
                N = width * height * num_base_anchors, width and height
                are the sizes of the corresponding feature lavel,
                num_base_anchors is the number of anchors for that level.
        """
        assert self.num_levels == len(featmap_sizes)
        multi_level_anchors = []
        for i in range(self.num_levels):
            anchors = self.single_level_grid_anchors(
                self.base_anchors[i].to(device),
                featmap_sizes[i],
                self.strides[i],
                device=device)
            multi_level_anchors.append(anchors)
        return multi_level_anchors 

def centers_to_bboxes(self, point_list):
        """Get bboxes according to center points.

        Only used in :class:`MaxIoUAssigner`.
        """
        bbox_list = []
        for i_img, point in enumerate(point_list):
            bbox = []
            for i_lvl in range(len(self.point_strides)):
                scale = self.point_base_scale * self.point_strides[i_lvl] * 0.5
                bbox_shift = torch.Tensor([-scale, -scale, scale,
                                           scale]).view(1, 4).type_as(point[0])
                bbox_center = torch.cat(
                    [point[i_lvl][:, :2], point[i_lvl][:, :2]], dim=1)
                bbox.append(bbox_center + bbox_shift)
            bbox_list.append(bbox)
        return bbox_list 

def roi_rescale(self, rois, scale_factor):
        """Scale RoI coordinates by scale factor.

        Args:
            rois (torch.Tensor): RoI (Region of Interest), shape (n, 5)
            scale_factor (float): Scale factor that RoI will be multiplied by.

        Returns:
            torch.Tensor: Scaled RoI.
        """

        cx = (rois[:, 1] + rois[:, 3]) * 0.5
        cy = (rois[:, 2] + rois[:, 4]) * 0.5
        w = rois[:, 3] - rois[:, 1]
        h = rois[:, 4] - rois[:, 2]
        new_w = w * scale_factor
        new_h = h * scale_factor
        x1 = cx - new_w * 0.5
        x2 = cx + new_w * 0.5
        y1 = cy - new_h * 0.5
        y2 = cy + new_h * 0.5
        new_rois = torch.stack((rois[:, 0], x1, y1, x2, y2), dim=-1)
        return new_rois 

def update(self, gt, pred):
    """
    gt, pred are tensors of size (..., 1, H, W) in the range [0, 1].
    """
    C, H, W = gt.size()[-3:]
    if isinstance(gt, torch.Tensor):
      gt = Variable(gt)
    if isinstance(pred, torch.Tensor):
      pred = Variable(pred)

    mse_score = self.mse_loss(pred, gt)
    eps = 1e-4
    pred.data[pred.data < eps] = eps
    pred.data[pred.data > 1 - eps] = 1 -eps
    bce_score = self.bce_loss(pred, gt)
    bce_score = bce_score.item() * C * H * W
    mse_score = mse_score.item() * C * H * W
    self.bce_results.append(bce_score)
    self.mse_results.append(mse_score) 

def smooth_l1_loss(pred, target, beta=1.0):
    """Smooth L1 loss.

    Args:
        pred (torch.Tensor): The prediction.
        target (torch.Tensor): The learning target of the prediction.
        beta (float, optional): The threshold in the piecewise function.
            Defaults to 1.0.

    Returns:
        torch.Tensor: Calculated loss
    """
    assert beta > 0
    assert pred.size() == target.size() and target.numel() > 0
    diff = torch.abs(pred - target)
    loss = torch.where(diff < beta, 0.5 * diff * diff / beta,
                       diff - 0.5 * beta)
    return loss 

def forward(self,
                pred,
                target,
                weight=None,
                avg_factor=None,
                reduction_override=None):
        """Forward function.

        Args:
            pred (torch.Tensor): The prediction.
            target (torch.Tensor): The learning target of the prediction.
            weight (torch.Tensor, optional): The weight of loss for each
                prediction. Defaults to None.
            avg_factor (int, optional): Average factor that is used to average
                the loss. Defaults to None.
            reduction_override (str, optional): The reduction method used to
                override the original reduction method of the loss.
                Defaults to None.
        """
        assert reduction_override in (None, 'none', 'mean', 'sum')
        reduction = (
            reduction_override if reduction_override else self.reduction)
        loss_bbox = self.loss_weight * l1_loss(
            pred, target, weight, reduction=reduction, avg_factor=avg_factor)
        return loss_bbox 

def rel_roi_point_to_rel_img_point(rois,
                                   rel_roi_points,
                                   img_shape,
                                   spatial_scale=1.):
    """Convert roi based relative point coordinates to image based absolute
    point coordinates.

    Args:
        rois (Tensor): RoIs or BBoxes, shape (N, 4) or (N, 5)
        rel_roi_points (Tensor): Point coordinates inside RoI, relative to
            RoI, location, range (0, 1), shape (N, P, 2)
        img_shape (tuple): (height, width) of image or feature map.
        spatial_scale (float): Scale points by this factor. Default: 1.

    Returns:
        Tensor: Image based relative point coordinates for sampling,
            shape (N, P, 2)
    """

    abs_img_point = rel_roi_point_to_abs_img_point(rois, rel_roi_points)
    rel_img_point = abs_img_point_to_rel_img_point(abs_img_point, img_shape,
                                                   spatial_scale)

    return rel_img_point 

def point_sample(input, points, align_corners=False, **kwargs):
    """A wrapper around :function:`grid_sample` to support 3D point_coords
    tensors Unlike :function:`torch.nn.functional.grid_sample` it assumes
    point_coords to lie inside [0, 1] x [0, 1] square.

    Args:
        input (Tensor): Feature map, shape (N, C, H, W).
        points (Tensor): Image based absolute point coordinates (normalized),
            range [0, 1] x [0, 1], shape (N, P, 2) or (N, Hgrid, Wgrid, 2).
        align_corners (bool): Whether align_corners. Default: False

    Returns:
        Tensor: Features of `point` on `input`, shape (N, C, P) or
            (N, C, Hgrid, Wgrid).
    """

    add_dim = False
    if points.dim() == 3:
        add_dim = True
        points = points.unsqueeze(2)
    output = F.grid_sample(
        input, denormalize(points), align_corners=align_corners, **kwargs)
    if add_dim:
        output = output.squeeze(3)
    return output 

def __call__(self, results):
        """Call function to convert image in results to :obj:`torch.Tensor` and
        transpose the channel order.

        Args:
            results (dict): Result dict contains the image data to convert.

        Returns:
            dict: The result dict contains the image converted
                to :obj:`torch.Tensor` and transposed to (C, H, W) order.
        """
        for key in self.keys:
            img = results[key]
            if len(img.shape) < 3:
                img = np.expand_dims(img, -1)
            results[key] = to_tensor(img.transpose(2, 0, 1))
        return results 

def scale_boxes(bboxes, scale):
    """Expand an array of boxes by a given scale.

    Args:
        bboxes (Tensor): Shape (m, 4)
        scale (float): The scale factor of bboxes

    Returns:
        (Tensor): Shape (m, 4). Scaled bboxes
    """
    assert bboxes.size(1) == 4
    w_half = (bboxes[:, 2] - bboxes[:, 0]) * .5
    h_half = (bboxes[:, 3] - bboxes[:, 1]) * .5
    x_c = (bboxes[:, 2] + bboxes[:, 0]) * .5
    y_c = (bboxes[:, 3] + bboxes[:, 1]) * .5

    w_half *= scale
    h_half *= scale

    boxes_scaled = torch.zeros_like(bboxes)
    boxes_scaled[:, 0] = x_c - w_half
    boxes_scaled[:, 2] = x_c + w_half
    boxes_scaled[:, 1] = y_c - h_half
    boxes_scaled[:, 3] = y_c + h_half
    return boxes_scaled 

def is_located_in(points, bboxes):
    """Are points located in bboxes.

    Args:
      points (Tensor): Points, shape: (m, 2).
      bboxes (Tensor): Bounding boxes, shape: (n, 4).

    Return:
      Tensor: Flags indicating if points are located in bboxes, shape: (m, n).
    """
    assert points.size(1) == 2
    assert bboxes.size(1) == 4
    return (points[:, 0].unsqueeze(1) > bboxes[:, 0].unsqueeze(0)) & \
           (points[:, 0].unsqueeze(1) < bboxes[:, 2].unsqueeze(0)) & \
           (points[:, 1].unsqueeze(1) > bboxes[:, 1].unsqueeze(0)) & \
           (points[:, 1].unsqueeze(1) < bboxes[:, 3].unsqueeze(0)) 

def bbox_flip(bboxes, img_shape, direction='horizontal'):
    """Flip bboxes horizontally or vertically.

    Args:
        bboxes (Tensor): Shape (..., 4*k)
        img_shape (tuple): Image shape.
        direction (str): Flip direction, options are "horizontal" and
            "vertical". Default: "horizontal"


    Returns:
        Tensor: Flipped bboxes.
    """
    assert bboxes.shape[-1] % 4 == 0
    assert direction in ['horizontal', 'vertical']
    flipped = bboxes.clone()
    if direction == 'vertical':
        flipped[..., 1::4] = img_shape[0] - bboxes[..., 3::4]
        flipped[..., 3::4] = img_shape[0] - bboxes[..., 1::4]
    else:
        flipped[:, 0::4] = img_shape[1] - bboxes[:, 2::4]
        flipped[:, 2::4] = img_shape[1] - bboxes[:, 0::4]
    return flipped 

def bbox2roi(bbox_list):
    """Convert a list of bboxes to roi format.

    Args:
        bbox_list (list[Tensor]): a list of bboxes corresponding to a batch
            of images.

    Returns:
        Tensor: shape (n, 5), [batch_ind, x1, y1, x2, y2]
    """
    rois_list = []
    for img_id, bboxes in enumerate(bbox_list):
        if bboxes.size(0) > 0:
            img_inds = bboxes.new_full((bboxes.size(0), 1), img_id)
            rois = torch.cat([img_inds, bboxes[:, :4]], dim=-1)
        else:
            rois = bboxes.new_zeros((0, 5))
        rois_list.append(rois)
    rois = torch.cat(rois_list, 0)
    return rois 

def roi2bbox(rois):
    """Convert rois to bounding box format.

    Args:
        rois (torch.Tensor): RoIs with the shape (n, 5) where the first
            column indicates batch id of each RoI.

    Returns:
        list[torch.Tensor]: Converted boxes of corresponding rois.
    """
    bbox_list = []
    img_ids = torch.unique(rois[:, 0].cpu(), sorted=True)
    for img_id in img_ids:
        inds = (rois[:, 0] == img_id.item())
        bbox = rois[inds, 1:]
        bbox_list.append(bbox)
    return bbox_list 

def bbox2result(bboxes, labels, num_classes):
    """Convert detection results to a list of numpy arrays.

    Args:
        bboxes (Tensor): shape (n, 5)
        labels (Tensor): shape (n, )
        num_classes (int): class number, including background class

    Returns:
        list(ndarray): bbox results of each class
    """
    if bboxes.shape[0] == 0:
        return [np.zeros((0, 5), dtype=np.float32) for i in range(num_classes)]
    else:
        bboxes = bboxes.cpu().numpy()
        labels = labels.cpu().numpy()
        return [bboxes[labels == i, :] for i in range(num_classes)] 

def distance2bbox(points, distance, max_shape=None):
    """Decode distance prediction to bounding box.

    Args:
        points (Tensor): Shape (n, 2), [x, y].
        distance (Tensor): Distance from the given point to 4
            boundaries (left, top, right, bottom).
        max_shape (tuple): Shape of the image.

    Returns:
        Tensor: Decoded bboxes.
    """
    x1 = points[:, 0] - distance[:, 0]
    y1 = points[:, 1] - distance[:, 1]
    x2 = points[:, 0] + distance[:, 2]
    y2 = points[:, 1] + distance[:, 3]
    if max_shape is not None:
        x1 = x1.clamp(min=0, max=max_shape[1])
        y1 = y1.clamp(min=0, max=max_shape[0])
        x2 = x2.clamp(min=0, max=max_shape[1])
        y2 = y2.clamp(min=0, max=max_shape[0])
    return torch.stack([x1, y1, x2, y2], -1) 

def random_choice(self, gallery, num):
        """Random select some elements from the gallery.

        If `gallery` is a Tensor, the returned indices will be a Tensor;
        If `gallery` is a ndarray or list, the returned indices will be a
        ndarray.

        Args:
            gallery (Tensor | ndarray | list): indices pool.
            num (int): expected sample num.

        Returns:
            Tensor or ndarray: sampled indices.
        """
        assert len(gallery) >= num

        is_tensor = isinstance(gallery, torch.Tensor)
        if not is_tensor:
            gallery = torch.tensor(
                gallery, dtype=torch.long, device=torch.cuda.current_device())
        perm = torch.randperm(gallery.numel(), device=gallery.device)[:num]
        rand_inds = gallery[perm]
        if not is_tensor:
            rand_inds = rand_inds.cpu().numpy()
        return rand_inds 

def sample(self, assign_result, bboxes, gt_bboxes, **kwargs):
        """Directly returns the positive and negative indices  of samples.

        Args:
            assign_result (:obj:`AssignResult`): Assigned results
            bboxes (torch.Tensor): Bounding boxes
            gt_bboxes (torch.Tensor): Ground truth boxes

        Returns:
            :obj:`SamplingResult`: sampler results
        """
        pos_inds = torch.nonzero(
            assign_result.gt_inds > 0, as_tuple=False).squeeze(-1).unique()
        neg_inds = torch.nonzero(
            assign_result.gt_inds == 0, as_tuple=False).squeeze(-1).unique()
        gt_flags = bboxes.new_zeros(bboxes.shape[0], dtype=torch.uint8)
        sampling_result = SamplingResult(pos_inds, neg_inds, bboxes, gt_bboxes,
                                         assign_result, gt_flags)
        return sampling_result 

def random_choice(gallery, num):
        """Randomly select some elements from the gallery.

        If `gallery` is a Tensor, the returned indices will be a Tensor;
        If `gallery` is a ndarray or list, the returned indices will be a
        ndarray.

        Args:
            gallery (Tensor | ndarray | list): indices pool.
            num (int): expected sample num.

        Returns:
            Tensor or ndarray: sampled indices.
        """
        assert len(gallery) >= num

        is_tensor = isinstance(gallery, torch.Tensor)
        if not is_tensor:
            gallery = torch.tensor(
                gallery, dtype=torch.long, device=torch.cuda.current_device())
        perm = torch.randperm(gallery.numel(), device=gallery.device)[:num]
        rand_inds = gallery[perm]
        if not is_tensor:
            rand_inds = rand_inds.cpu().numpy()
        return rand_inds 

def encode(self, bboxes, gt_bboxes):
        """Get box regression transformation deltas that can be used to
        transform the ``bboxes`` into the ``gt_bboxes``.

        Args:
            bboxes (torch.Tensor): source boxes, e.g., object proposals.
            gt_bboxes (torch.Tensor): target of the transformation, e.g.,
                ground-truth boxes.

        Returns:
            torch.Tensor: Box transformation deltas
        """
        assert bboxes.size(0) == gt_bboxes.size(0)
        assert bboxes.size(-1) == gt_bboxes.size(-1) == 4
        encoded_bboxes = legacy_bbox2delta(bboxes, gt_bboxes, self.means,
                                           self.stds)
        return encoded_bboxes 

def decode(self,
               bboxes,
               pred_bboxes,
               max_shape=None,
               wh_ratio_clip=16 / 1000):
        """Apply transformation `pred_bboxes` to `boxes`.

        Args:
            boxes (torch.Tensor): Basic boxes.
            pred_bboxes (torch.Tensor): Encoded boxes with shape
            max_shape (tuple[int], optional): Maximum shape of boxes.
                Defaults to None.
            wh_ratio_clip (float, optional): The allowed ratio between
                width and height.

        Returns:
            torch.Tensor: Decoded boxes.
        """
        assert pred_bboxes.size(0) == bboxes.size(0)
        decoded_bboxes = legacy_delta2bbox(bboxes, pred_bboxes, self.means,
                                           self.stds, max_shape, wh_ratio_clip)

        return decoded_bboxes 

def encode(self, bboxes, gt_bboxes):
        """Get box regression transformation deltas that can be used to
        transform the ``bboxes`` into the ``gt_bboxes``.

        Args:
            bboxes (torch.Tensor): Source boxes, e.g., object proposals.
            gt_bboxes (torch.Tensor): Target of the transformation, e.g.,
                ground-truth boxes.

        Returns:
            torch.Tensor: Box transformation deltas
        """

        assert bboxes.size(0) == gt_bboxes.size(0)
        assert bboxes.size(-1) == gt_bboxes.size(-1) == 4
        encoded_bboxes = bbox2delta(bboxes, gt_bboxes, self.means, self.stds)
        return encoded_bboxes 

def decode(self,
               bboxes,
               pred_bboxes,
               max_shape=None,
               wh_ratio_clip=16 / 1000):
        """Apply transformation `pred_bboxes` to `boxes`.

        Args:
            boxes (torch.Tensor): Basic boxes.
            pred_bboxes (torch.Tensor): Encoded boxes with shape
            max_shape (tuple[int], optional): Maximum shape of boxes.
                Defaults to None.
            wh_ratio_clip (float, optional): The allowed ratio between
                width and height.

        Returns:
            torch.Tensor: Decoded boxes.
        """

        assert pred_bboxes.size(0) == bboxes.size(0)
        decoded_bboxes = delta2bbox(bboxes, pred_bboxes, self.means, self.stds,
                                    max_shape, wh_ratio_clip)

        return decoded_bboxes 

def encode(self, bboxes, gt_bboxes):
        """Get box regression transformation deltas that can be used to
        transform the ``bboxes`` into the ``gt_bboxes`` in the (top, left,
        bottom, right) order.

        Args:
            bboxes (torch.Tensor): source boxes, e.g., object proposals.
            gt_bboxes (torch.Tensor): target of the transformation, e.g.,
                ground truth boxes.

        Returns:
            torch.Tensor: Box transformation deltas
        """
        assert bboxes.size(0) == gt_bboxes.size(0)
        assert bboxes.size(-1) == gt_bboxes.size(-1) == 4
        encoded_bboxes = bboxes2tblr(
            bboxes, gt_bboxes, normalizer=self.normalizer)
        return encoded_bboxes 

def decode(self, bboxes, pred_bboxes, max_shape=None):
        """Apply transformation `pred_bboxes` to `boxes`.

        Args:
            boxes (torch.Tensor): Basic boxes.
            pred_bboxes (torch.Tensor): Encoded boxes with shape
            max_shape (tuple[int], optional): Maximum shape of boxes.
                Defaults to None.

        Returns:
            torch.Tensor: Decoded boxes.
        """
        assert pred_bboxes.size(0) == bboxes.size(0)
        decoded_bboxes = tblr2bboxes(
            bboxes,
            pred_bboxes,
            normalizer=self.normalizer,
            max_shape=max_shape)

        return decoded_bboxes 

def tensor2imgs(tensor, mean=(0, 0, 0), std=(1, 1, 1), to_rgb=True):
    """Convert tensor to images.

    Args:
        tensor (torch.Tensor): Tensor that contains multiple images
        mean (tuple[float], optional): Mean of images. Defaults to (0, 0, 0).
        std (tuple[float], optional): Standard deviation of images.
            Defaults to (1, 1, 1).
        to_rgb (bool, optional): Whether convert the images to RGB format.
            Defaults to True.

    Returns:
        list[np.ndarray]: A list that contains multiple images.
    """
    num_imgs = tensor.size(0)
    mean = np.array(mean, dtype=np.float32)
    std = np.array(std, dtype=np.float32)
    imgs = []
    for img_id in range(num_imgs):
        img = tensor[img_id, ...].cpu().numpy().transpose(1, 2, 0)
        img = mmcv.imdenormalize(
            img, mean, std, to_bgr=to_rgb).astype(np.uint8)
        imgs.append(np.ascontiguousarray(img))
    return imgs 

def calc_region(bbox, ratio, featmap_size=None):
    """Calculate a proportional bbox region.

    The bbox center are fixed and the new h' and w' is h * ratio and w * ratio.

    Args:
        bbox (Tensor): Bboxes to calculate regions, shape (n, 4).
        ratio (float): Ratio of the output region.
        featmap_size (tuple): Feature map size used for clipping the boundary.

    Returns:
        tuple: x1, y1, x2, y2
    """
    x1 = torch.round((1 - ratio) * bbox[0] + ratio * bbox[2]).long()
    y1 = torch.round((1 - ratio) * bbox[1] + ratio * bbox[3]).long()
    x2 = torch.round(ratio * bbox[0] + (1 - ratio) * bbox[2]).long()
    y2 = torch.round(ratio * bbox[1] + (1 - ratio) * bbox[3]).long()
    if featmap_size is not None:
        x1 = x1.clamp(min=0, max=featmap_size[1])
        y1 = y1.clamp(min=0, max=featmap_size[0])
        x2 = x2.clamp(min=0, max=featmap_size[1])
        y2 = y2.clamp(min=0, max=featmap_size[0])
    return (x1, y1, x2, y2) 

def gen_base_anchors(self):
        """Generate base anchors.

        Returns:
            list(torch.Tensor): Base anchors of a feature grid in multiple
                feature levels.
        """
        multi_level_base_anchors = []
        for i, base_size in enumerate(self.base_sizes):
            center = None
            if self.centers is not None:
                center = self.centers[i]
            multi_level_base_anchors.append(
                self.gen_single_level_base_anchors(
                    base_size,
                    scales=self.scales,
                    ratios=self.ratios,
                    center=center))
        return multi_level_base_anchors 

def pose_inv_full(pose):
  '''
  param pose: N x 6
  Inverse the 2x3 transformer matrix.
  '''
  N, _ = pose.size()
  b = pose.view(N, 2, 3)[:, :, 2:]
  # A^{-1}
  # Calculate determinant
  determinant = (pose[:, 0] * pose[:, 4] - pose[:, 1] * pose[:, 3] + 1e-8).view(N, 1)
  indices = Variable(torch.LongTensor([4, 1, 3, 0]).cuda())
  scale = Variable(torch.Tensor([1, -1, -1, 1]).cuda())
  A_inv = torch.index_select(pose, 1, indices) * scale / determinant
  A_inv = A_inv.view(N, 2, 2)
  # b' = - A^{-1} b
  b_inv = - A_inv.matmul(b).view(N, 2, 1)
  transformer_inv = torch.cat([A_inv, b_inv], dim=2)
  return transformer_inv 

def _sample_neg(self,
                    assign_result,
                    num_expected,
                    bboxes=None,
                    feats=None,
                    **kwargs):
        """Sample negative boxes.

        Args:
            assign_result (:obj:`AssignResult`): Assigned results
            num_expected (int): Number of expected negative samples
            bboxes (torch.Tensor, optional): Boxes. Defaults to None.
            feats (list[torch.Tensor], optional): Multi-level features.
                Defaults to None.

        Returns:
            torch.Tensor: Indices  of negative samples
        """
        # Sample some hard negative samples
        neg_inds = torch.nonzero(assign_result.gt_inds == 0, as_tuple=False)
        if neg_inds.numel() != 0:
            neg_inds = neg_inds.squeeze(1)
        if len(neg_inds) <= num_expected:
            return neg_inds
        else:
            neg_labels = assign_result.labels.new_empty(
                neg_inds.size(0)).fill_(self.bbox_head.num_classes)
            return self.hard_mining(neg_inds, num_expected, bboxes[neg_inds],
                                    neg_labels, feats)