Python boxlist_ops.boxlist_nms方法代码示例

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
def filter_results(self, boxlist, num_classes):
        """Returns bounding-box detection results by thresholding on scores and
        applying non-maximum suppression (NMS).
        """
        # 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)
            )
            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.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]
        return result 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
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 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
def forward_for_single_feature_map(self, anchors, objectness, box_regression):
        """
        Arguments:
            anchors: list[BoxList]
            objectness: tensor of size N, A, H, W
            box_regression: tensor of size N, A * 4, H, W
        """
        device = objectness.device
        N, A, H, W = objectness.shape

        # put in the same format as anchors
        objectness = permute_and_flatten(objectness, N, A, 1, H, W).view(N, -1)
        objectness = objectness.sigmoid()

        box_regression = permute_and_flatten(box_regression, N, A, 4, H, W)

        num_anchors = A * H * W

        pre_nms_top_n = min(self.pre_nms_top_n, num_anchors)
        objectness, topk_idx = objectness.topk(pre_nms_top_n, dim=1, sorted=True)

        batch_idx = torch.arange(N, device=device)[:, None]
        box_regression = box_regression[batch_idx, topk_idx]

        image_shapes = [box.size for box in anchors]
        concat_anchors = torch.cat([a.bbox for a in anchors], dim=0)
        concat_anchors = concat_anchors.reshape(N, -1, 4)[batch_idx, topk_idx]

        proposals = self.box_coder.decode(
            box_regression.view(-1, 4), concat_anchors.view(-1, 4)
        )

        proposals = proposals.view(N, -1, 4)

        result = []
        for proposal, score, im_shape in zip(proposals, objectness, image_shapes):
            boxlist = BoxList(proposal, im_shape, mode="xyxy")
            boxlist.add_field("objectness", score)
            boxlist = boxlist.clip_to_image(remove_empty=False)
            boxlist = remove_small_boxes(boxlist, self.min_size)
            boxlist = boxlist_nms(
                boxlist,
                self.nms_thresh,
                max_proposals=self.post_nms_top_n,
                score_field="objectness",
            )
            result.append(boxlist)
        return result 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
def filter_results(self, boxlist, num_classes):
        """Returns bounding-box detection results by thresholding on scores and
        applying non-maximum suppression (NMS).
        """
        # 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)
        quad_boxes = boxlist.quad_bbox.reshape(-1, num_classes * 8)
        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]
            quad_boxes_j = quad_boxes[inds, j * 8 : (j + 1) * 8]
            boxlist_for_class = QuadBoxList(quad_boxes_j, boxlist.size, mode="xyxy")
            boxlist_for_class.bbox = boxes_j
            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)
            )
            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.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]
        return result 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
def forward_for_single_feature_map(self, anchors, objectness, box_regression, angle_cls, angle_regression):
        """
        Arguments:
            anchors: list[BoxList]
            objectness: tensor of size N, A, H, W
            box_regression: tensor of size N, A * 4, H, W
            angle_cls: tensor of size N, 6, H, W
            angle_reg: tensor of size N, 6, H, W
        """
        device = objectness.device
        N, A, H, W = objectness.shape

        # put in the same format as anchors
        objectness = objectness.permute(0, 2, 3, 1).reshape(N, -1)
        objectness = objectness.sigmoid()
        box_regression = box_regression.view(N, -1, 4, H, W).permute(0, 3, 4, 1, 2)
        box_regression = box_regression.reshape(N, -1, 4)



        num_anchors = A * H * W

        pre_nms_top_n = min(self.pre_nms_top_n, num_anchors)
        objectness, topk_idx = objectness.topk(pre_nms_top_n, dim=1, sorted=True)

        batch_idx = torch.arange(N, device=device)[:, None]
        box_regression = box_regression[batch_idx, topk_idx]

        image_shapes = [box.size for box in anchors]
        concat_anchors = torch.cat([a.bbox for a in anchors], dim=0)
        concat_anchors = concat_anchors.reshape(N, -1, 4)[batch_idx, topk_idx]

        proposals = self.box_coder.decode(
            box_regression.view(-1, 4), concat_anchors.view(-1, 4)
        )

        proposals = proposals.view(N, -1, 4)

        result = []
        for proposal, score, im_shape in zip(proposals, objectness, image_shapes):
            boxlist = BoxList(proposal, im_shape, mode="xyxy")
            boxlist.add_field("objectness", score)
            boxlist = boxlist.clip_to_image(remove_empty=False)
            boxlist = remove_small_boxes(boxlist, self.min_size)
            boxlist = boxlist_nms(
                boxlist,
                self.nms_thresh,
                max_proposals=self.post_nms_top_n,
                score_field="objectness",
            )
            result.append(boxlist)
        return result 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
def filter_results(self, boxlist, num_classes):
        """Returns bounding-box detection results by thresholding on scores and
        applying non-maximum suppression (NMS).
        """
        # 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, score_field="scores"
            )
            num_labels = len(boxlist_for_class)
            boxlist_for_class.add_field(
                "labels", torch.full((num_labels,), j, dtype=torch.int64, device=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.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]
        return result 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
def forward_for_single_feature_map(self, anchors, objectness, box_regression):
        """
        Arguments:
            anchors: list[BoxList]
            objectness: tensor of size N, A, H, W
            box_regression: tensor of size N, A * 4, H, W
        """
        device = objectness.device
        N, A, H, W = objectness.shape

        # put in the same format as anchors
        objectness = objectness.permute(0, 2, 3, 1).reshape(N, -1)
        objectness = objectness.sigmoid()
        box_regression = box_regression.view(N, -1, 4, H, W).permute(0, 3, 4, 1, 2)
        box_regression = box_regression.reshape(N, -1, 4)

        num_anchors = A * H * W

        pre_nms_top_n = min(self.pre_nms_top_n, num_anchors)
        objectness, topk_idx = objectness.topk(pre_nms_top_n, dim=1, sorted=True)

        batch_idx = torch.arange(N, device=device)[:, None]
        box_regression = box_regression[batch_idx, topk_idx]

        image_shapes = [box.size for box in anchors]
        concat_anchors = torch.cat([a.bbox for a in anchors], dim=0)
        concat_anchors = concat_anchors.reshape(N, -1, 4)[batch_idx, topk_idx]

        proposals = self.box_coder.decode(
            box_regression.view(-1, 4), concat_anchors.view(-1, 4)
        )

        proposals = proposals.view(N, -1, 4)

        result = []
        for proposal, score, im_shape in zip(proposals, objectness, image_shapes):
            boxlist = BoxList(proposal, im_shape, mode="xyxy")
            boxlist.add_field("objectness", score)
            boxlist = boxlist.clip_to_image(remove_empty=False)
            boxlist = remove_small_boxes(boxlist, self.min_size)
            boxlist = boxlist_nms(
                boxlist,
                self.nms_thresh,
                max_proposals=self.post_nms_top_n,
                score_field="objectness",
            )
            result.append(boxlist)
        return result 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
def filter_results(self, boxlist, num_classes):
        """Returns bounding-box detection results by thresholding on scores and
        applying non-maximum suppression (NMS).
        """
        # 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
        if self.imbalanced_decider is None:
            inds_all = scores > self.score_thresh
        else:
            inds_all = self.imbalanced_decider(scores)
        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)
            )
            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.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]
        return result 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
def filter_results(self, boxlist, num_classes):
        """Returns bounding-box detection results by thresholding on scores and
        applying non-maximum suppression (NMS).
        """
        # 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
        no_background = int(self.free_anchor)
        for j in range(1 - no_background, num_classes - no_background):
            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, score_field="scores"
            )
            num_labels = len(boxlist_for_class)
            boxlist_for_class.add_field(
                "labels", torch.full((num_labels,), j + no_background, dtype=torch.int64, device=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.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]
        return result 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
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, 81):
                inds = (labels == j).nonzero().view(-1)
                if len(inds) == 0:
                    continue

                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)

            if len(result) > 0:
                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)
            else:
                empty_boxlist = BoxList(torch.zeros(1, 4).to('cuda'), boxlist.size)
                empty_boxlist.add_field(
                    "labels", torch.LongTensor([1]).to('cuda'))
                empty_boxlist.add_field(
                    "scores", torch.Tensor([0.01]).to('cuda'))
                results.append(empty_boxlist)
        return results 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
def select_over_all_levels_with(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, 81):
                inds = (labels == j).nonzero().view(-1)
                if len(inds) == 0:
                    continue

                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)

            if len(result) > 0:
                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)
            else:
                empty_boxlist = BoxList(torch.zeros(1, 4).to('cuda'), boxlist.size)
                empty_boxlist.add_field(
                    "labels", torch.LongTensor([1]).to('cuda'))
                empty_boxlist.add_field(
                    "scores", torch.Tensor([0.01]).to('cuda'))
                results.append(empty_boxlist)
        return results 

# 需要导入模块: from maskrcnn_benchmark.structures import boxlist_ops [as 别名]
# 或者: from maskrcnn_benchmark.structures.boxlist_ops import boxlist_nms [as 别名]
def select_over_all_levels(self, boxlists):
        num_images = len(boxlists)
        results = []
        for i in range(num_images):
            if len(boxlists[i]) == 0:
                results.append([])
                continue

            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, 81):
                inds = (labels == j).nonzero().view(-1)
                if len(inds) == 0:
                    continue

                boxlist_for_class = boxlist[inds]
                #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