Python utils.batch_slice() Examples

The following are 16 code examples of utils.batch_slice(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module utils , or try the search function .
Example #1
Source File: model.py    From Mask-RCNN-Pedestrian-Detection with MIT License 6 votes vote down vote up
def call(self, inputs):
        rois = inputs[0]
        mrcnn_class = inputs[1]
        mrcnn_bbox = inputs[2]
        image_meta = inputs[3]

        # Run detection refinement graph on each item in the batch
        _, _, window, _ = parse_image_meta_graph(image_meta)
        window = norm_boxes_graph(window, self.config.IMAGE_SHAPE[:2])
        detections_batch = utils.batch_slice(
            [rois, mrcnn_class, mrcnn_bbox, window],
            lambda x, y, w, z: refine_detections_graph(x, y, w, z, self.config),
            self.config.IMAGES_PER_GPU)

        # Reshape output
        # [batch, num_detections, (y1, x1, y2, x2, class_score)] in
        # normalized coordinates
        return tf.reshape(
            detections_batch,
            [self.config.BATCH_SIZE, self.config.DETECTION_MAX_INSTANCES, 6]) 
Example #2
Source File: model.py    From PyTorch-Luna16 with Apache License 2.0 6 votes vote down vote up
def call(self, inputs):
        rois = inputs[0]
        mrcnn_class = inputs[1]
        mrcnn_bbox = inputs[2]
        image_meta = inputs[3]

        # Run detection refinement graph on each item in the batch
        _, _, window, _ = parse_image_meta_graph(image_meta)
        detections_batch = utils.batch_slice(
            [rois, mrcnn_class, mrcnn_bbox, window],
            lambda x, y, w, z: refine_detections_graph(x, y, w, z, self.config),
            self.config.IMAGES_PER_GPU)

        # Reshape output
        # [batch, num_detections, (y1, x1, y2, x2, class_score)] in pixels
        return tf.reshape(
            detections_batch,
            [self.config.BATCH_SIZE, self.config.DETECTION_MAX_INSTANCES, 6]) 
Example #3
Source File: model.py    From segmentation-unet-maskrcnn with MIT License 5 votes vote down vote up
def call(self, inputs):
        proposals = inputs[0]
        gt_class_ids = inputs[1]
        gt_boxes = inputs[2]
        gt_masks = inputs[3]

        # Slice the batch and run a graph for each slice
        # TODO: Rename target_bbox to target_deltas for clarity
        names = ["rois", "target_class_ids", "target_bbox", "target_mask"]
        outputs = utils.batch_slice(
            [proposals, gt_class_ids, gt_boxes, gt_masks],
            lambda w, x, y, z: detection_targets_graph(
                w, x, y, z, self.config),
            self.config.IMAGES_PER_GPU, names=names)
        return outputs 
Example #4
Source File: model.py    From Mask-RCNN-Pedestrian-Detection with MIT License 5 votes vote down vote up
def call(self, inputs):
        proposals = inputs[0]
        gt_class_ids = inputs[1]
        gt_boxes = inputs[2]
        gt_masks = inputs[3]

        # Slice the batch and run a graph for each slice
        # TODO: Rename target_bbox to target_deltas for clarity
        names = ["rois", "target_class_ids", "target_bbox", "target_mask"]
        outputs = utils.batch_slice(
            [proposals, gt_class_ids, gt_boxes, gt_masks],
            lambda w, x, y, z: detection_targets_graph(
                w, x, y, z, self.config),
            self.config.IMAGES_PER_GPU, names=names)
        return outputs 
Example #5
Source File: model.py    From raster-deep-learning with Apache License 2.0 5 votes vote down vote up
def call(self, inputs):
        proposals = inputs[0]
        gt_class_ids = inputs[1]
        gt_boxes = inputs[2]
        gt_masks = inputs[3]

        # Slice the batch and run a graph for each slice
        # TODO: Rename target_bbox to target_deltas for clarity
        names = ["rois", "target_class_ids", "target_bbox", "target_mask"]
        outputs = utils.batch_slice(
            [proposals, gt_class_ids, gt_boxes, gt_masks],
            lambda w, x, y, z: detection_targets_graph(
                w, x, y, z, self.config),
            self.config.IMAGES_PER_GPU, names=names)
        return outputs 
Example #6
Source File: model.py    From raster-deep-learning with Apache License 2.0 5 votes vote down vote up
def call(self, inputs):
        rois = inputs[0]
        mrcnn_class = inputs[1]
        mrcnn_bbox = inputs[2]
        image_meta = inputs[3]

        # Get windows of images in normalized coordinates. Windows are the area
        # in the image that excludes the padding.
        # Use the shape of the first image in the batch to normalize the window
        # because we know that all images get resized to the same size.
        m = parse_image_meta_graph(image_meta)
        image_shape = m['image_shape'][0]
        window = norm_boxes_graph(m['window'], image_shape[:2])
        
        # Run detection refinement graph on each item in the batch
        detections_batch = utils.batch_slice(
            [rois, mrcnn_class, mrcnn_bbox, window],
            lambda x, y, w, z: refine_detections_graph(x, y, w, z, self.config),
            self.config.IMAGES_PER_GPU)

        # Reshape output
        # [batch, num_detections, (y1, x1, y2, x2, class_score)] in
        # normalized coordinates
        return tf.reshape(
            detections_batch,
            [self.config.BATCH_SIZE, self.config.DETECTION_MAX_INSTANCES, 6]) 
Example #7
Source File: model.py    From i.ann.maskrcnn with GNU General Public License v2.0 5 votes vote down vote up
def call(self, inputs):
        proposals = inputs[0]
        gt_class_ids = inputs[1]
        gt_boxes = inputs[2]
        gt_masks = inputs[3]

        # Slice the batch and run a graph for each slice
        # TODO: Rename target_bbox to target_deltas for clarity
        names = ["rois", "target_class_ids", "target_bbox", "target_mask"]
        outputs = utils.batch_slice(
            [proposals, gt_class_ids, gt_boxes, gt_masks],
            lambda w, x, y, z: detection_targets_graph(
                w, x, y, z, self.config),
            self.config.IMAGES_PER_GPU, names=names)
        return outputs 
Example #8
Source File: model.py    From i.ann.maskrcnn with GNU General Public License v2.0 5 votes vote down vote up
def call(self, inputs):
        rois = inputs[0]
        mrcnn_class = inputs[1]
        mrcnn_bbox = inputs[2]
        image_meta = inputs[3]

        # Get windows of images in normalized coordinates. Windows are the area
        # in the image that excludes the padding.
        # Use the shape of the first image in the batch to normalize the window
        # because we know that all images get resized to the same size.
        m = parse_image_meta_graph(image_meta)
        image_shape = m['image_shape'][0]
        window = norm_boxes_graph(m['window'], image_shape[:2])

        # Run detection refinement graph on each item in the batch
        detections_batch = utils.batch_slice(
            [rois, mrcnn_class, mrcnn_bbox, window],
            lambda x, y, w, z: refine_detections_graph(x, y, w, z, self.config),
            self.config.IMAGES_PER_GPU)

        # Reshape output
        # [batch, num_detections, (y1, x1, y2, x2, class_id, class_score)] in
        # normalized coordinates
        return tf.reshape(
            detections_batch,
            [self.config.BATCH_SIZE, self.config.DETECTION_MAX_INSTANCES, 6]) 
Example #9
Source File: model.py    From latte with Apache License 2.0 5 votes vote down vote up
def call(self, inputs):
        proposals = inputs[0]
        gt_class_ids = inputs[1]
        gt_boxes = inputs[2]
        gt_masks = inputs[3]

        # Slice the batch and run a graph for each slice
        # TODO: Rename target_bbox to target_deltas for clarity
        names = ["rois", "target_class_ids", "target_bbox", "target_mask"]
        outputs = utils.batch_slice(
            [proposals, gt_class_ids, gt_boxes, gt_masks],
            lambda w, x, y, z: detection_targets_graph(
                w, x, y, z, self.config),
            self.config.IMAGES_PER_GPU, names=names)
        return outputs 
Example #10
Source File: model.py    From PyTorch-Luna16 with Apache License 2.0 5 votes vote down vote up
def call(self, inputs):
        proposals = inputs[0]
        gt_class_ids = inputs[1]
        gt_boxes = inputs[2]
        gt_masks = inputs[3]

        # Slice the batch and run a graph for each slice
        # TODO: Rename target_bbox to target_deltas for clarity
        names = ["rois", "target_class_ids", "target_bbox", "target_mask"]
        outputs = utils.batch_slice(
            [proposals, gt_class_ids, gt_boxes, gt_masks],
            lambda w, x, y, z: detection_targets_graph(
                w, x, y, z, self.config),
            self.config.IMAGES_PER_GPU, names=names)
        return outputs 
Example #11
Source File: model.py    From segmentation-unet-maskrcnn with MIT License 4 votes vote down vote up
def call(self, inputs):
        # Box Scores. Use the foreground class confidence. [Batch, num_rois, 1]
        scores = inputs[0][:, :, 1]
        # Box deltas [batch, num_rois, 4]
        deltas = inputs[1]
        deltas = deltas * np.reshape(self.config.RPN_BBOX_STD_DEV, [1, 1, 4])
        # Base anchors
        anchors = self.anchors

        # Improve performance by trimming to top anchors by score
        # and doing the rest on the smaller subset.
        pre_nms_limit = min(6000, self.anchors.shape[0])
        ix = tf.nn.top_k(scores, pre_nms_limit, sorted=True,
                         name="top_anchors").indices
        scores = utils.batch_slice([scores, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        deltas = utils.batch_slice([deltas, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        anchors = utils.batch_slice(ix, lambda x: tf.gather(anchors, x),
                                    self.config.IMAGES_PER_GPU,
                                    names=["pre_nms_anchors"])

        # Apply deltas to anchors to get refined anchors.
        # [batch, N, (y1, x1, y2, x2)]
        boxes = utils.batch_slice([anchors, deltas],
                                  lambda x, y: apply_box_deltas_graph(x, y),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors"])

        # Clip to image boundaries. [batch, N, (y1, x1, y2, x2)]
        height, width = self.config.IMAGE_SHAPE[:2]
        window = np.array([0, 0, height, width]).astype(np.float32)
        boxes = utils.batch_slice(boxes,
                                  lambda x: clip_boxes_graph(x, window),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors_clipped"])

        # Filter out small boxes
        # According to Xinlei Chen's paper, this reduces detection accuracy
        # for small objects, so we're skipping it.

        # Normalize dimensions to range of 0 to 1.
        normalized_boxes = boxes / np.array([[height, width, height, width]])

        # Non-max suppression
        def nms(normalized_boxes, scores):
            indices = tf.image.non_max_suppression(
                normalized_boxes, scores, self.proposal_count,
                self.nms_threshold, name="rpn_non_max_suppression")
            proposals = tf.gather(normalized_boxes, indices)
            # Pad if needed
            padding = tf.maximum(self.proposal_count - tf.shape(proposals)[0], 0)
            proposals = tf.pad(proposals, [(0, padding), (0, 0)])
            return proposals
        proposals = utils.batch_slice([normalized_boxes, scores], nms,
                                      self.config.IMAGES_PER_GPU)
        return proposals 
Example #12
Source File: model.py    From Mask-RCNN-Pedestrian-Detection with MIT License 4 votes vote down vote up
def call(self, inputs):
        # Box Scores. Use the foreground class confidence. [Batch, num_rois, 1]
        scores = inputs[0][:, :, 1]
        # Box deltas [batch, num_rois, 4]
        deltas = inputs[1]
        deltas = deltas * np.reshape(self.config.RPN_BBOX_STD_DEV, [1, 1, 4])
        # Base anchors
        anchors = self.anchors

        # Improve performance by trimming to top anchors by score
        # and doing the rest on the smaller subset.
        pre_nms_limit = min(6000, self.anchors.shape[0])
        ix = tf.nn.top_k(scores, pre_nms_limit, sorted=True,
                         name="top_anchors").indices
        scores = utils.batch_slice([scores, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        deltas = utils.batch_slice([deltas, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        anchors = utils.batch_slice(ix, lambda x: tf.gather(anchors, x),
                                    self.config.IMAGES_PER_GPU,
                                    names=["pre_nms_anchors"])

        # Apply deltas to anchors to get refined anchors.
        # [batch, N, (y1, x1, y2, x2)]
        boxes = utils.batch_slice([anchors, deltas],
                                  lambda x, y: apply_box_deltas_graph(x, y),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors"])

        # Clip to image boundaries. [batch, N, (y1, x1, y2, x2)]
        height, width = self.config.IMAGE_SHAPE[:2]
        window = np.array([0, 0, height, width]).astype(np.float32)
        boxes = utils.batch_slice(boxes,
                                  lambda x: clip_boxes_graph(x, window),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors_clipped"])

        # Filter out small boxes
        # According to Xinlei Chen's paper, this reduces detection accuracy
        # for small objects, so we're skipping it.

        # Normalize coordinates
        normalized_boxes = norm_boxes_graph(boxes, self.config.IMAGE_SHAPE[:2])

        # Non-max suppression
        def nms(normalized_boxes, scores):
            indices = tf.image.non_max_suppression(
                normalized_boxes, scores, self.proposal_count,
                self.nms_threshold, name="rpn_non_max_suppression")
            proposals = tf.gather(normalized_boxes, indices)
            # Pad if needed
            padding = tf.maximum(self.proposal_count - tf.shape(proposals)[0], 0)
            proposals = tf.pad(proposals, [(0, padding), (0, 0)])
            return proposals
        proposals = utils.batch_slice([normalized_boxes, scores], nms,
                                      self.config.IMAGES_PER_GPU)
        return proposals 
Example #13
Source File: model.py    From raster-deep-learning with Apache License 2.0 4 votes vote down vote up
def call(self, inputs):
        # Box Scores. Use the foreground class confidence. [Batch, num_rois, 1]
        scores = inputs[0][:, :, 1]
        # Box deltas [batch, num_rois, 4]
        deltas = inputs[1]
        deltas = deltas * np.reshape(self.config.RPN_BBOX_STD_DEV, [1, 1, 4])
        # Anchors
        anchors = inputs[2]

        # Improve performance by trimming to top anchors by score
        # and doing the rest on the smaller subset.
        pre_nms_limit = tf.minimum(6000, tf.shape(anchors)[1])
        ix = tf.nn.top_k(scores, pre_nms_limit, sorted=True,
                         name="top_anchors").indices
        scores = utils.batch_slice([scores, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        deltas = utils.batch_slice([deltas, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        pre_nms_anchors = utils.batch_slice([anchors, ix], lambda a, x: tf.gather(a, x),
                                    self.config.IMAGES_PER_GPU,
                                    names=["pre_nms_anchors"])

        # Apply deltas to anchors to get refined anchors.
        # [batch, N, (y1, x1, y2, x2)]
        boxes = utils.batch_slice([pre_nms_anchors, deltas],
                                  lambda x, y: apply_box_deltas_graph(x, y),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors"])

        # Clip to image boundaries. Since we're in normalized coordinates,
        # clip to 0..1 range. [batch, N, (y1, x1, y2, x2)]
        window = np.array([0, 0, 1, 1], dtype=np.float32)
        boxes = utils.batch_slice(boxes,
                                  lambda x: clip_boxes_graph(x, window),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors_clipped"])

        # Filter out small boxes
        # According to Xinlei Chen's paper, this reduces detection accuracy
        # for small objects, so we're skipping it.

        # Non-max suppression
        def nms(boxes, scores):
            indices = tf.image.non_max_suppression(
                boxes, scores, self.proposal_count,
                self.nms_threshold, name="rpn_non_max_suppression")
            proposals = tf.gather(boxes, indices)
            # Pad if needed
            padding = tf.maximum(self.proposal_count - tf.shape(proposals)[0], 0)
            proposals = tf.pad(proposals, [(0, padding), (0, 0)])
            return proposals
        proposals = utils.batch_slice([boxes, scores], nms,
                                      self.config.IMAGES_PER_GPU)
        return proposals 
Example #14
Source File: model.py    From i.ann.maskrcnn with GNU General Public License v2.0 4 votes vote down vote up
def call(self, inputs):
        # Box Scores. Use the foreground class confidence. [Batch, num_rois, 1]
        scores = inputs[0][:, :, 1]
        # Box deltas [batch, num_rois, 4]
        deltas = inputs[1]
        deltas = deltas * np.reshape(self.config.RPN_BBOX_STD_DEV, [1, 1, 4])
        # Anchors
        anchors = inputs[2]

        # Improve performance by trimming to top anchors by score
        # and doing the rest on the smaller subset.
        pre_nms_limit = tf.minimum(self.config.PRE_NMS_LIMIT, tf.shape(anchors)[1])
        ix = tf.nn.top_k(scores, pre_nms_limit, sorted=True,
                         name="top_anchors").indices
        scores = utils.batch_slice([scores, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        deltas = utils.batch_slice([deltas, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        pre_nms_anchors = utils.batch_slice([anchors, ix], lambda a, x: tf.gather(a, x),
                                    self.config.IMAGES_PER_GPU,
                                    names=["pre_nms_anchors"])

        # Apply deltas to anchors to get refined anchors.
        # [batch, N, (y1, x1, y2, x2)]
        boxes = utils.batch_slice([pre_nms_anchors, deltas],
                                  lambda x, y: apply_box_deltas_graph(x, y),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors"])

        # Clip to image boundaries. Since we're in normalized coordinates,
        # clip to 0..1 range. [batch, N, (y1, x1, y2, x2)]
        window = np.array([0, 0, 1, 1], dtype=np.float32)
        boxes = utils.batch_slice(boxes,
                                  lambda x: clip_boxes_graph(x, window),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors_clipped"])

        # Filter out small boxes
        # According to Xinlei Chen's paper, this reduces detection accuracy
        # for small objects, so we're skipping it.

        # Non-max suppression
        def nms(boxes, scores):
            indices = tf.image.non_max_suppression(
                boxes, scores, self.proposal_count,
                self.nms_threshold, name="rpn_non_max_suppression")
            proposals = tf.gather(boxes, indices)
            # Pad if needed
            padding = tf.maximum(self.proposal_count - tf.shape(proposals)[0], 0)
            proposals = tf.pad(proposals, [(0, padding), (0, 0)])
            return proposals
        proposals = utils.batch_slice([boxes, scores], nms,
                                      self.config.IMAGES_PER_GPU)
        return proposals 
Example #15
Source File: model.py    From latte with Apache License 2.0 4 votes vote down vote up
def call(self, inputs):
        # Box Scores. Use the foreground class confidence. [Batch, num_rois, 1]
        scores = inputs[0][:, :, 1]
        # Box deltas [batch, num_rois, 4]
        deltas = inputs[1]
        deltas = deltas * np.reshape(self.config.RPN_BBOX_STD_DEV, [1, 1, 4])
        # Base anchors
        anchors = self.anchors

        # Improve performance by trimming to top anchors by score
        # and doing the rest on the smaller subset.
        pre_nms_limit = min(6000, self.anchors.shape[0])
        ix = tf.nn.top_k(scores, pre_nms_limit, sorted=True,
                         name="top_anchors").indices
        scores = utils.batch_slice([scores, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        deltas = utils.batch_slice([deltas, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        anchors = utils.batch_slice(ix, lambda x: tf.gather(anchors, x),
                                    self.config.IMAGES_PER_GPU,
                                    names=["pre_nms_anchors"])

        # Apply deltas to anchors to get refined anchors.
        # [batch, N, (y1, x1, y2, x2)]
        boxes = utils.batch_slice([anchors, deltas],
                                  lambda x, y: apply_box_deltas_graph(x, y),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors"])

        # Clip to image boundaries. [batch, N, (y1, x1, y2, x2)]
        height, width = self.config.IMAGE_SHAPE[:2]
        window = np.array([0, 0, height, width]).astype(np.float32)
        boxes = utils.batch_slice(boxes,
                                  lambda x: clip_boxes_graph(x, window),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors_clipped"])

        # Filter out small boxes
        # According to Xinlei Chen's paper, this reduces detection accuracy
        # for small objects, so we're skipping it.

        # Normalize dimensions to range of 0 to 1.
        normalized_boxes = boxes / np.array([[height, width, height, width]])

        # Non-max suppression
        def nms(normalized_boxes, scores):
            indices = tf.image.non_max_suppression(
                normalized_boxes, scores, self.proposal_count,
                self.nms_threshold, name="rpn_non_max_suppression")
            proposals = tf.gather(normalized_boxes, indices)
            # Pad if needed
            padding = tf.maximum(self.proposal_count - tf.shape(proposals)[0], 0)
            proposals = tf.pad(proposals, [(0, padding), (0, 0)])
            return proposals
        proposals = utils.batch_slice([normalized_boxes, scores], nms,
                                      self.config.IMAGES_PER_GPU)
        return proposals 
Example #16
Source File: model.py    From PyTorch-Luna16 with Apache License 2.0 4 votes vote down vote up
def call(self, inputs):
        # Box Scores. Use the foreground class confidence. [Batch, num_rois, 1]
        scores = inputs[0][:, :, 1]
        # Box deltas [batch, num_rois, 4]
        deltas = inputs[1]
        deltas = deltas * np.reshape(self.config.RPN_BBOX_STD_DEV, [1, 1, 4])
        # Base anchors
        anchors = self.anchors

        # Improve performance by trimming to top anchors by score
        # and doing the rest on the smaller subset.
        pre_nms_limit = min(6000, self.anchors.shape[0])
        ix = tf.nn.top_k(scores, pre_nms_limit, sorted=True,
                         name="top_anchors").indices
        scores = utils.batch_slice([scores, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        deltas = utils.batch_slice([deltas, ix], lambda x, y: tf.gather(x, y),
                                   self.config.IMAGES_PER_GPU)
        anchors = utils.batch_slice(ix, lambda x: tf.gather(anchors, x),
                                    self.config.IMAGES_PER_GPU,
                                    names=["pre_nms_anchors"])

        # Apply deltas to anchors to get refined anchors.
        # [batch, N, (y1, x1, y2, x2)]
        boxes = utils.batch_slice([anchors, deltas],
                                  lambda x, y: apply_box_deltas_graph(x, y),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors"])

        # Clip to image boundaries. [batch, N, (y1, x1, y2, x2)]
        height, width = self.config.IMAGE_SHAPE[:2]
        window = np.array([0, 0, height, width]).astype(np.float32)
        boxes = utils.batch_slice(boxes,
                                  lambda x: clip_boxes_graph(x, window),
                                  self.config.IMAGES_PER_GPU,
                                  names=["refined_anchors_clipped"])

        # Filter out small boxes
        # According to Xinlei Chen's paper, this reduces detection accuracy
        # for small objects, so we're skipping it.

        # Normalize dimensions to range of 0 to 1.
        normalized_boxes = boxes / np.array([[height, width, height, width]])

        # Non-max suppression
        def nms(normalized_boxes, scores):
            indices = tf.image.non_max_suppression(
                normalized_boxes, scores, self.proposal_count,
                self.nms_threshold, name="rpn_non_max_suppression")
            proposals = tf.gather(normalized_boxes, indices)
            # Pad if needed
            padding = tf.maximum(self.proposal_count - tf.shape(proposals)[0], 0)
            proposals = tf.pad(proposals, [(0, padding), (0, 0)])
            return proposals
        proposals = utils.batch_slice([normalized_boxes, scores], nms,
                                      self.config.IMAGES_PER_GPU)
        return proposals