def rpn_proposals(self):
with tf.variable_scope('rpn_proposals'):
rpn_decode_boxes = encode_and_decode.decode_boxes(encode_boxes=self.rpn_encode_boxes,
reference_boxes=self.anchors,
scale_factors=self.scale_factors)
if not self.is_training: # when test, clip proposals to img boundaries
img_shape = tf.shape(self.img_batch)
rpn_decode_boxes = boxes_utils.clip_boxes_to_img_boundaries(rpn_decode_boxes, img_shape)
rpn_softmax_scores = slim.softmax(self.rpn_scores)
rpn_object_score = rpn_softmax_scores[:, 1] # second column represent object
if self.top_k_nms:
rpn_object_score, top_k_indices = tf.nn.top_k(rpn_object_score, k=self.top_k_nms)
rpn_decode_boxes = tf.gather(rpn_decode_boxes, top_k_indices)
valid_indices = nms.non_maximal_suppression(boxes=rpn_decode_boxes,
scores=rpn_object_score,
max_output_size=self.max_proposals_num,
iou_threshold=self.rpn_nms_iou_threshold)
valid_boxes = tf.gather(rpn_decode_boxes, valid_indices)
valid_scores = tf.gather(rpn_object_score, valid_indices)
rpn_proposals_boxes, rpn_proposals_scores = tf.cond(
tf.less(tf.shape(valid_boxes)[0], self.max_proposals_num),
lambda: boxes_utils.padd_boxes_with_zeros(valid_boxes, valid_scores,
self.max_proposals_num),
lambda: (valid_boxes, valid_scores))
return rpn_proposals_boxes, rpn_proposals_scores
def rpn_proposals(self):
with tf.variable_scope('rpn_proposals'):
rpn_decode_boxes = encode_and_decode.decode_boxes(
encode_boxes=self.rpn_encode_boxes,
reference_boxes=self.anchors,
scale_factors=self.scale_factors)
# if not self.is_training: # when test, clip proposals to img boundaries
# img_shape = tf.shape(self.img_batch)
# rpn_decode_boxes = boxes_utils.clip_boxes_to_img_boundaries(rpn_decode_boxes, img_shape)
rpn_softmax_scores = slim.softmax(self.rpn_scores)
rpn_object_score = rpn_softmax_scores[:,
1] # second column represent object
if self.top_k_nms:
rpn_object_score, top_k_indices = tf.nn.top_k(rpn_object_score,
k=self.top_k_nms)
rpn_decode_boxes = tf.gather(rpn_decode_boxes, top_k_indices)
if not cfgs.USE_HORIZONTAL_NMS:
valid_indices = nms_rotate.nms_rotate(
decode_boxes=rpn_decode_boxes,
scores=rpn_object_score,
iou_threshold=self.rpn_nms_iou_threshold,
max_output_size=self.max_proposals_num,
use_angle_condition=self.use_angles_condition,
angle_threshold=self.anchor_angle_threshold,
use_gpu=cfgs.NMS_USE_GPU)
############################################################################################################
else:
rpn_decode_boxes_convert = tf.py_func(
coordinate_convert.forward_convert,
inp=[rpn_decode_boxes],
Tout=tf.float32)
rpn_decode_boxes_convert = tf.reshape(
rpn_decode_boxes_convert,
[tf.shape(rpn_decode_boxes)[0], 8])
x1, y1, x2, y2, x3, y3, x4, y4 = tf.unstack(
rpn_decode_boxes_convert, axis=1)
x = tf.transpose(tf.stack([x1, x2, x3, x4]))
y = tf.transpose(tf.stack([y1, y2, y3, y4]))
min_x = tf.reduce_min(x, axis=1)
max_x = tf.reduce_max(x, axis=1)
min_y = tf.reduce_min(y, axis=1)
max_y = tf.reduce_max(y, axis=1)
rpn_decode_boxes_convert = tf.transpose(
tf.stack([min_x, min_y, max_x, max_y]))
valid_indices = tf.image.non_max_suppression(
boxes=rpn_decode_boxes_convert,
scores=rpn_object_score,
max_output_size=self.max_proposals_num,
iou_threshold=self.rpn_nms_iou_threshold,
name='rpn_horizontal_nms')
############################################################################################################
valid_boxes = tf.gather(rpn_decode_boxes, valid_indices)
valid_scores = tf.gather(rpn_object_score, valid_indices)
rpn_proposals_boxes, rpn_proposals_scores = tf.cond(
tf.less(tf.shape(valid_boxes)[0], self.max_proposals_num),
lambda: boxes_utils.padd_boxes_with_zeros(
valid_boxes, valid_scores, self.max_proposals_num), lambda:
(valid_boxes, valid_scores))
return rpn_proposals_boxes, rpn_proposals_scores