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])
def call(self, inputs):
proposals = inputs[0]
gt_boxes = inputs[1]
# 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"]
outputs = utils.batch_slice(
[proposals, gt_boxes],
lambda x, y: detection_targets_graph(
x, y, self.config),
self.config.IMAGES_PER_GPU, names=names)
return outputs
def call(self, inputs):
rois = inputs[0]
mrcnn_class = inputs[1]
mrcnn_bbox = inputs[2]
# Run detection refinement graph on each item in the batch
detections_batch = utils.batch_slice(
[rois, mrcnn_class, mrcnn_bbox],
lambda x, y, z: refine_detections_graph(x, y, 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])
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