示例#1
0
    def forward(self, anchors, objectness, box_regression, targets=None):
        """
        Arguments:
            anchors: list[list[BoxList]]
            objectness: list[tensor]
            box_regression: list[tensor]
        Returns:
            boxlists (list[BoxList]): the post-processed anchors, after
                applying box decoding and NMS
        """
        sampled_boxes = []
        num_levels = len(objectness)
        anchors = list(zip(*anchors))
        for a, o, b in zip(anchors, objectness, box_regression):
            sampled_boxes.append(self.forward_for_single_feature_map(a, o, b))

        boxlists = list(zip(*sampled_boxes))
        boxlists = [cat_boxlist(boxlist) for boxlist in boxlists]

        if num_levels > 1:
            boxlists = self.select_over_all_levels(boxlists)

        # append ground-truth bboxes to proposals
        if self.training and self.add_gt:
            boxlists = self.add_gt_proposals(boxlists, targets)

        return boxlists
示例#2
0
def cat_boxlist_with_keypoints(boxlists):
    assert all(boxlist.has_field("keypoints") for boxlist in boxlists)

    kp = [boxlist.get_field("keypoints").keypoints for boxlist in boxlists]
    kp = cat(kp, 0)

    fields = boxlists[0].get_fields()
    fields = [field for field in fields if field != "keypoints"]

    boxlists = [boxlist.copy_with_fields(fields) for boxlist in boxlists]
    boxlists = cat_boxlist(boxlists)
    boxlists.add_field("keypoints", kp)
    return boxlists
示例#3
0
    def filter_results(self, boxlist, num_classes):

        # unwrap the boxlist to avoid additional overhead.
        # if we had multi-class NMS, we could perform this directly on the boxlist
        boxes = boxlist.bbox.reshape(-1, num_classes * 4)
        scores = boxlist.get_field("scores").reshape(-1, num_classes)

        device = scores.device
        result = []
        # Apply threshold on detection probabilities and apply NMS
        # Skip j = 0, because it's the background class
        inds_all = scores > self.score_thresh
        for j in range(1, num_classes):
            inds = inds_all[:, j].nonzero().squeeze(1)
            scores_j = scores[inds, j]
            boxes_j = boxes[inds, j * 4:(j + 1) * 4]
            boxlist_for_class = BoxList(boxes_j, boxlist.size, mode="xyxy")
            boxlist_for_class.add_field("scores", scores_j)
            boxlist_for_class = boxlist_nms(boxlist_for_class, self.nms)
            num_labels = len(boxlist_for_class)
            boxlist_for_class.add_field(
                "labels",
                torch.full((num_labels, ), j, dtype=torch.int64,
                           device=device))
            #boxlist_for_class.add_field(
            # we use full_like to allow tracing with flexible shape
            #    "labels", torch.full_like(boxlist_for_class.bbox[:, 0], j, dtype=torch.int64)
            #)
            result.append(boxlist_for_class)

        result = cat_boxlist(result)
        number_of_detections = len(result)

        if number_of_detections > self.detections_per_img > 0:
            cls_scores = result.get_field("scores")
            image_thresh, _ = torch.kthvalue(
                cls_scores.cpu(),
                number_of_detections - self.detections_per_img + 1)
            keep = cls_scores >= image_thresh.item()
            keep = torch.nonzero(keep).squeeze(1)
            result = result[keep]

        ## this part is changed for onnx export
        #scores = result.get_field('scores')
        #if self.onnx_export:
        #    keep = self.detections_to_keep_onnx(scores)
        #else:
        #    keep = self.detections_to_keep(scores)
        #result = result[keep]

        return result
    def select_over_all_levels(self, boxlists):
        num_images = len(boxlists)
        results = []
        for i in range(num_images):
            scores = boxlists[i].get_field("scores")
            labels = boxlists[i].get_field("labels")
            boxes = boxlists[i].bbox
            boxlist = boxlists[i]
            result = []
            # skip the background
            for j in range(1, self.num_classes):
                inds = (labels == j).nonzero().view(-1)

                scores_j = scores[inds]
                boxes_j = boxes[inds, :].view(-1, 4)
                boxlist_for_class = BoxList(boxes_j, boxlist.size, mode="xyxy")
                boxlist_for_class.add_field("scores", scores_j)
                boxlist_for_class = boxlist_nms(boxlist_for_class,
                                                self.nms_thresh,
                                                score_field="scores")
                num_labels = len(boxlist_for_class)
                boxlist_for_class.add_field(
                    "labels",
                    torch.full((num_labels, ),
                               j,
                               dtype=torch.int64,
                               device=scores.device))
                result.append(boxlist_for_class)

            result = cat_boxlist(result)
            number_of_detections = len(result)

            # Limit to max_per_image detections **over all classes**
            if number_of_detections > self.fpn_post_nms_top_n > 0:
                cls_scores = result.get_field("scores")
                image_thresh, _ = torch.kthvalue(
                    cls_scores.cpu(),
                    number_of_detections - self.fpn_post_nms_top_n + 1)
                keep = cls_scores >= image_thresh.item()
                keep = torch.nonzero(keep).squeeze(1)
                result = result[keep]
            results.append(result)
        return results
示例#5
0
    def __call__(self, anchors, objectness, box_regression, targets):
        """
        Arguments:
            anchors (list[BoxList])
            objectness (list[Tensor])
            box_regression (list[Tensor])
            targets (list[BoxList])
        Returns:
            objectness_loss (Tensor)
            box_loss (Tensor
        """
        anchors = [cat_boxlist(anchors_per_image) for anchors_per_image in anchors]
        labels, regression_targets = self.prepare_targets(anchors, targets)
        sampled_pos_inds, sampled_neg_inds = self.fg_bg_sampler(labels)
        sampled_pos_inds = torch.nonzero(torch.cat(sampled_pos_inds, dim=0)).squeeze(1)
        sampled_neg_inds = torch.nonzero(torch.cat(sampled_neg_inds, dim=0)).squeeze(1)

        sampled_inds = torch.cat([sampled_pos_inds, sampled_neg_inds], dim=0)

        objectness, box_regression = \
                concat_box_prediction_layers(objectness, box_regression)

        objectness = objectness.squeeze()

        labels = torch.cat(labels, dim=0)
        regression_targets = torch.cat(regression_targets, dim=0)

        box_loss = smooth_l1_loss(
            box_regression[sampled_pos_inds],
            regression_targets[sampled_pos_inds],
            beta=1.0 / 9,
            size_average=False,
        ) / (sampled_inds.numel())

        objectness_loss = F.binary_cross_entropy_with_logits(
            objectness[sampled_inds], labels[sampled_inds]
        )

        return objectness_loss, box_loss
    def __call__(self, anchors, box_cls, box_regression, targets):
        """
        Arguments:
            anchors (list[BoxList])
            box_cls (list[Tensor])
            box_regression (list[Tensor])
            targets (list[BoxList])
        Returns:
            retinanet_cls_loss (Tensor)
            retinanet_regression_loss (Tensor
        """
        anchors = [cat_boxlist(anchors_per_image) for anchors_per_image in anchors]
        labels, regression_targets = self.prepare_targets(anchors, targets)

        N = len(labels)
        box_cls, box_regression = \
                concat_box_prediction_layers(box_cls, box_regression)

        labels = torch.cat(labels, dim=0)
        regression_targets = torch.cat(regression_targets, dim=0)
        pos_inds = torch.nonzero(labels > 0).squeeze(1)

        retinanet_regression_loss = smooth_l1_loss(
            box_regression[pos_inds],
            regression_targets[pos_inds],
            beta=self.bbox_reg_beta,
            size_average=False,
        ) / (max(1, pos_inds.numel() * self.regress_norm))

        labels = labels.int()

        retinanet_cls_loss = self.box_cls_loss_func(
            box_cls,
            labels
        ) / (pos_inds.numel() + N)

        return retinanet_cls_loss, retinanet_regression_loss
示例#7
0
    def add_gt_proposals(self, proposals, targets):
        """
        Arguments:
            proposals: list[BoxList]
            targets: list[BoxList]
        """
        # Get the device we're operating on
        device = proposals[0].bbox.device

        #gt_boxes = [target.copy_with_fields([]) for target in targets]

        gt_boxes = []
        for target in targets:
            if len(target) > 0:
                gt_boxes.append(target.copy_with_fields([]))
            else:
                gt_boxes.append(target)

        # later cat of bbox requires all fields to be present for all bbox
        # so we need to add a dummy for objectness that's missing
        for gt_box in gt_boxes:
            if len(gt_box) > 0:
                gt_box.add_field("objectness",
                                 torch.ones(len(gt_box), device=device))

        #proposals = [
        #    cat_boxlist((proposal, gt_box))
        #    for proposal, gt_box in zip(proposals, gt_boxes)
        #]
        new_proposals = []
        for proposal, gt_box in zip(proposals, gt_boxes):
            if len(gt_box) > 0:
                new_proposals.append(cat_boxlist((proposal, gt_box)))
            else:
                new_proposals.append(proposal)
        return new_proposals