Python mrcnn.utils.batch_slice() Examples
The following are 28
code examples of mrcnn.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
mrcnn.utils
, or try the search function
.
.
Example #1
| Source File: model_mod_rgb.py From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 | 5 votes |
|
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 #2
| Source File: model.py From cvpr-2018-autonomous-driving-autopilot-solution with MIT License | 5 votes |
|
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 #3
| Source File: model_inceptionresnet.py From cvpr-2018-autonomous-driving-autopilot-solution with MIT License | 5 votes |
|
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 #4
| Source File: model_inceptionresnet.py From cvpr-2018-autonomous-driving-autopilot-solution with MIT License | 5 votes |
|
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 deepdiy with MIT License | 5 votes |
|
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 #6
| Source File: model.py From deepdiy with MIT License | 5 votes |
|
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 #7
| Source File: model.py From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 | 5 votes |
|
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 #8
| Source File: model.py From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 | 5 votes |
|
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 #9
| Source File: model_mod_mpan.py From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 | 5 votes |
|
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_mod_rgb.py From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 | 5 votes |
|
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 bird_species_classification with MIT License | 5 votes |
|
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 #12
| Source File: model.py From dataiku-contrib with Apache License 2.0 | 5 votes |
|
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 #13
| Source File: model.py From dataiku-contrib with Apache License 2.0 | 5 votes |
|
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 #14
| Source File: model.py From deep-learning-explorer with Apache License 2.0 | 5 votes |
|
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 #15
| Source File: model.py From deep-learning-explorer with Apache License 2.0 | 5 votes |
|
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 #16
| Source File: model.py From bird_species_classification with MIT License | 5 votes |
|
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 #17
| Source File: model.py From PanopticSegmentation with MIT License | 5 votes |
|
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 #18
| Source File: model.py From PanopticSegmentation with MIT License | 5 votes |
|
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 #19
| Source File: model.py From deep-learning-explorer with Apache License 2.0 | 4 votes |
|
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 #20
| Source File: model.py From cvpr-2018-autonomous-driving-autopilot-solution with MIT License | 4 votes |
|
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 #21
| Source File: model.py From PanopticSegmentation with MIT License | 4 votes |
|
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 #22
| Source File: model_inceptionresnet.py From cvpr-2018-autonomous-driving-autopilot-solution with MIT License | 4 votes |
|
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 #23
| Source File: model.py From deepdiy with MIT License | 4 votes |
|
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 #24
| Source File: model.py From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 | 4 votes |
|
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 #25
| Source File: model_mod_mpan.py From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 | 4 votes |
|
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. # boost all # 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 #26
| Source File: model.py From dataiku-contrib with Apache License 2.0 | 4 votes |
|
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 #27
| Source File: model.py From bird_species_classification with MIT License | 4 votes |
|
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 #28
| Source File: model_mod_rgb.py From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 | 4 votes |
|
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. # boost all # 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
