Example #1
0
 def test_batched_nms_rotated_0_degree_cuda(self):
     # torch.manual_seed(0)
     N = 2000
     num_classes = 50
     boxes, scores = self._create_tensors(N)
     idxs = torch.randint(0, num_classes, (N, ))
     rotated_boxes = torch.zeros(N, 5)
     rotated_boxes[:, 0] = (boxes[:, 0] + boxes[:, 2]) / 2.0
     rotated_boxes[:, 1] = (boxes[:, 1] + boxes[:, 3]) / 2.0
     rotated_boxes[:, 2] = boxes[:, 2] - boxes[:, 0]
     rotated_boxes[:, 3] = boxes[:, 3] - boxes[:, 1]
     err_msg = "Rotated NMS with 0 degree is incompatible with horizontal NMS for IoU={}"
     for iou in [0.2, 0.5, 0.8]:
         backup = boxes.clone()
         keep_ref = batched_nms(boxes.cuda(), scores.cuda(), idxs, iou)
         assert torch.allclose(boxes,
                               backup), "boxes modified by batched_nms"
         backup = rotated_boxes.clone()
         keep = batched_nms_rotated(rotated_boxes.cuda(), scores.cuda(),
                                    idxs, iou)
         assert torch.allclose(
             rotated_boxes,
             backup), "rotated_boxes modified by batched_nms_rotated"
         self.assertLessEqual(nms_edit_distance(keep, keep_ref), 1,
                              err_msg.format(iou))
Example #2
0
def merge_branch_instances(instances, num_branch, nms_thrsh, topk_per_image):
    """
    Merge detection results from different branches of TridentNet.
    Return detection results by applying non-maximum suppression (NMS) on bounding boxes
    and keep the unsuppressed boxes and other instances (e.g mask) if any.

    Args:
        instances (list[Instances]): A list of N * num_branch instances that store detection
            results. Contain N images and each image has num_branch instances.
        num_branch (int): Number of branches used for merging detection results for each image.
        nms_thresh (float):  The threshold to use for box non-maximum suppression. Value in [0, 1].
        topk_per_image (int): The number of top scoring detections to return. Set < 0 to return
            all detections.

    Returns:
        results: (list[Instances]): A list of N instances, one for each image in the batch,
            that stores the topk most confidence detections after merging results from multiple
            branches.
    """
    if num_branch == 1:
        return instances

    batch_size = len(instances) // num_branch
    results = []
    for i in range(batch_size):
        instance = Instances.cat(
            [instances[i + batch_size * j] for j in range(num_branch)])

        # Apply per-class NMS
        keep = batched_nms(instance.pred_boxes.tensor, instance.scores,
                           instance.pred_classes, nms_thrsh)
        keep = keep[:topk_per_image]
        result = instance[keep]

        results.append(result)

    return results
Example #3
0
def find_top_rpn_proposals(
        proposals,
        pred_objectness_logits,
        images,
        nms_thresh,
        pre_nms_topk,
        post_nms_topk,
        min_box_side_len,
        training,  # pylint: disable=W0613
):
    """
    For each feature map, select the `pre_nms_topk` highest scoring proposals,
    apply NMS, clip proposals, and remove small boxes. Return the `post_nms_topk`
    highest scoring proposals among all the feature maps if `training` is True,
    otherwise, returns the highest `post_nms_topk` scoring proposals for each
    feature map.

    Args:
        proposals (list[Tensor]): A list of L tensors. Tensor i has shape (N, Hi*Wi*A, 4).
            All proposal predictions on the feature maps.
        pred_objectness_logits (list[Tensor]): A list of L tensors. Tensor i has shape (N, Hi*Wi*A).
        images (ImageList): Input images as an :class:`ImageList`.
        nms_thresh (float): IoU threshold to use for NMS
        pre_nms_topk (int): number of top k scoring proposals to keep before applying NMS.
            When RPN is run on multiple feature maps (as in FPN) this number is per
            feature map.
        post_nms_topk (int): number of top k scoring proposals to keep after applying NMS.
            When RPN is run on multiple feature maps (as in FPN) this number is total,
            over all feature maps.
        min_box_side_len (float): minimum proposal box side length in pixels (absolute units
            wrt input images).
        training (bool): True if proposals are to be used in training, otherwise False.
            This arg exists only to support a legacy bug; look for the "NB: Legacy bug ..."
            comment.

    Returns:
        proposals (list[Instances]): list of N Instances. The i-th Instances
            stores post_nms_topk object proposals for image i.
    """
    image_sizes = images.image_sizes  # in (h, w) order
    num_images = len(image_sizes)
    device = proposals[0].device

    # 1. Select top-k anchor for every level and every image
    topk_scores = []  # #lvl Tensor, each of shape N x topk
    topk_proposals = []
    level_ids = []  # #lvl Tensor, each of shape (topk,)
    batch_idx = torch.arange(num_images, device=device)
    for level_id, proposals_i, logits_i in zip(itertools.count(), proposals,
                                               pred_objectness_logits):
        Hi_Wi_A = logits_i.shape[1]
        num_proposals_i = min(pre_nms_topk, Hi_Wi_A)

        # sort is faster than topk (https://github.com/pytorch/pytorch/issues/22812)
        # topk_scores_i, topk_idx = logits_i.topk(num_proposals_i, dim=1)
        logits_i, idx = logits_i.sort(descending=True, dim=1)
        topk_scores_i = logits_i[batch_idx, :num_proposals_i]
        topk_idx = idx[batch_idx, :num_proposals_i]

        # each is N x topk
        topk_proposals_i = proposals_i[batch_idx[:, None],
                                       topk_idx]  # N x topk x 4

        topk_proposals.append(topk_proposals_i)
        topk_scores.append(topk_scores_i)
        level_ids.append(
            torch.full((num_proposals_i, ),
                       level_id,
                       dtype=torch.int64,
                       device=device))

    # 2. Concat all levels together
    topk_scores = cat(topk_scores, dim=1)
    topk_proposals = cat(topk_proposals, dim=1)
    level_ids = cat(level_ids, dim=0)

    # 3. For each image, run a per-level NMS, and choose topk results.
    results = []
    for n, image_size in enumerate(image_sizes):
        boxes = Boxes(topk_proposals[n])
        scores_per_img = topk_scores[n]
        # boxes.clip(image_size)

        # filter empty boxes
        keep = boxes.nonempty(threshold=min_box_side_len)
        lvl = level_ids
        if keep.sum().item() != len(boxes):
            boxes, scores_per_img, lvl = boxes[keep], scores_per_img[
                keep], level_ids[keep]

        keep = batched_nms(boxes.tensor, scores_per_img, lvl, nms_thresh)
        # In Detectron1, there was different behavior during training vs. testing.
        # (https://github.com/facebookresearch/Detectron/issues/459)
        # During training, topk is over the proposals from *all* images in the training batch.
        # During testing, it is over the proposals for each image separately.
        # As a result, the training behavior becomes batch-dependent,
        # and the configuration "POST_NMS_TOPK_TRAIN" end up relying on the batch size.
        # This bug is addressed in cvpods to make the behavior independent of batch size.
        keep = keep[:post_nms_topk]

        res = Instances(image_size)
        res.proposal_boxes = boxes[keep]
        res.objectness_logits = scores_per_img[keep]
        results.append(res)
    return results
Example #4
0
    def inference_single_image(self, box_cls, box_delta, anchors, image_size):
        """
        Single-image inference. Return bounding-box detection results by thresholding
        on scores and applying non-maximum suppression (NMS).

        Arguments:
            box_cls (list[Tensor]): list of #feature levels. Each entry contains
                tensor of size (H x W x A, K)
            box_delta (list[Tensor]): Same shape as 'box_cls' except that K becomes 4.
            anchors (list[Boxes]): list of #feature levels. Each entry contains
                a Boxes object, which contains all the anchors for that
                image in that feature level.
            image_size (tuple(H, W)): a tuple of the image height and width.

        Returns:
            Same as `inference`, but for only one image.
        """
        boxes_all = []
        scores_all = []
        class_idxs_all = []

        # Iterate over every feature level
        for box_cls_i, box_reg_i, anchors_i in zip(box_cls, box_delta,
                                                   anchors):
            # (HxWxAxK,)
            box_cls_i = box_cls_i.flatten().sigmoid_()

            # Keep top k top scoring indices only.
            num_topk = min(self.topk_candidates, box_reg_i.size(0))
            # torch.sort is actually faster than .topk (at least on GPUs)
            predicted_prob, topk_idxs = box_cls_i.sort(descending=True)
            predicted_prob = predicted_prob[:num_topk]
            topk_idxs = topk_idxs[:num_topk]

            # filter out the proposals with low confidence score
            keep_idxs = predicted_prob > self.score_threshold
            predicted_prob = predicted_prob[keep_idxs]
            topk_idxs = topk_idxs[keep_idxs]

            anchor_idxs = topk_idxs // self.num_classes
            classes_idxs = topk_idxs % self.num_classes

            box_reg_i = box_reg_i[anchor_idxs]
            anchors_i = anchors_i[anchor_idxs]
            # predict boxes
            predicted_boxes = self.box2box_transform.apply_deltas(
                box_reg_i, anchors_i.tensor)

            boxes_all.append(predicted_boxes)
            scores_all.append(predicted_prob)
            class_idxs_all.append(classes_idxs)

        boxes_all, scores_all, class_idxs_all = [
            cat(x) for x in [boxes_all, scores_all, class_idxs_all]
        ]
        keep = batched_nms(boxes_all, scores_all, class_idxs_all,
                           self.nms_threshold)
        keep = keep[:self.max_detections_per_image]

        result = Instances(image_size)
        result.pred_boxes = Boxes(boxes_all[keep])
        result.scores = scores_all[keep]
        result.pred_classes = class_idxs_all[keep]
        return result