def decode_box(self, prior_bboxes, prior_variances):
mc = self.mc
print('self.mbox_loc:', self.mbox_loc)
mbox_loc_reshape = tf.reshape(self.mbox_loc, [mc.BATCH_SIZE, -1, 4])
delta_xmin, delta_ymin, delta_xmax, delta_ymax = tf.unstack(
mbox_loc_reshape, axis=2)
prior_bboxes_reshape = tf.reshape(prior_bboxes, [-1, 4])
prior_variances_reshape = tf.reshape(prior_variances, [-1, 4])
prior_width = prior_bboxes_reshape[:, 2] - prior_bboxes_reshape[:, 0]
prior_height = prior_bboxes_reshape[:, 3] - prior_bboxes_reshape[:, 1]
prior_center_x = (prior_bboxes_reshape[:, 0] +
prior_bboxes_reshape[:, 2]) / 2.
prior_center_y = (prior_bboxes_reshape[:, 1] +
prior_bboxes_reshape[:, 3]) / 2.
bbox_center_x = tf.identity(prior_variances_reshape[:, 0] *
delta_xmin * prior_width + prior_center_x)
bbox_center_y = tf.identity(prior_variances_reshape[:, 1] *
delta_ymin * prior_height + prior_center_y)
bbox_width = tf.identity(
util.safe_exp(prior_variances_reshape[:, 2] * delta_xmax,
mc.EXP_THRESH) * prior_width)
bbox_height = tf.identity(
util.safe_exp(prior_variances_reshape[:, 3] * delta_ymax,
mc.EXP_THRESH) * prior_height)
xmins, ymins, xmaxs, ymaxs = util.bbox_transform(
[bbox_center_x, bbox_center_y, bbox_width, bbox_height])
'''
xmins = tf.minimum(
tf.maximum(0.0, xmins), 1., name='bbox_xmin')
ymins = tf.minimum(
tf.maximum(0.0, ymins), 1., name='bbox_ymin')
xmaxs = tf.maximum(
tf.minimum(1., xmaxs), 0.0, name='bbox_xmax')
ymaxs = tf.maximum(
tf.minimum(1., ymaxs), 0.0, name='bbox_ymax')
'''
xmins *= mc.IMAGE_WIDTH
xmaxs *= mc.IMAGE_WIDTH
ymins *= mc.IMAGE_HEIGHT
ymaxs *= mc.IMAGE_HEIGHT
self.decode_boxes = tf.stack([xmins, ymins, xmaxs, ymaxs], axis=2)
self._add_act(self.decode_boxes, 'decode_boxes')
def _add_interpretation_graph(self):
"""Interpret NN output."""
mc = self.mc
with tf.variable_scope('interpret_output') as scope:
preds = self.preds
# probability
num_class_probs = mc.ANCHOR_PER_GRID * mc.CLASSES
self.pred_class_probs = tf.reshape(
tf.nn.softmax(
tf.reshape(preds[:, :, :, :num_class_probs],
[-1, mc.CLASSES])),
[mc.BATCH_SIZE, mc.ANCHORS, mc.CLASSES],
name='pred_class_probs')
# confidence
num_confidence_scores = mc.ANCHOR_PER_GRID + num_class_probs
self.pred_conf = tf.sigmoid(tf.reshape(
preds[:, :, :, num_class_probs:num_confidence_scores],
[mc.BATCH_SIZE, mc.ANCHORS]),
name='pred_confidence_score')
# bbox_delta
self.pred_box_delta = tf.reshape(preds[:, :, :,
num_confidence_scores:],
[mc.BATCH_SIZE, mc.ANCHORS, 4],
name='bbox_delta')
# number of object. Used to normalize bbox and classification loss
self.num_objects = tf.reduce_sum(self.input_mask,
name='num_objects')
with tf.variable_scope('bbox') as scope:
with tf.variable_scope('stretching'):
delta_x, delta_y, delta_w, delta_h = tf.unstack(
self.pred_box_delta, axis=2)
anchor_x = mc.ANCHOR_BOX[:, 0]
anchor_y = mc.ANCHOR_BOX[:, 1]
anchor_w = mc.ANCHOR_BOX[:, 2]
anchor_h = mc.ANCHOR_BOX[:, 3]
box_center_x = tf.identity(anchor_x + delta_x * anchor_w,
name='bbox_cx')
box_center_y = tf.identity(anchor_y + delta_y * anchor_h,
name='bbox_cy')
box_width = tf.identity(anchor_w *
util.safe_exp(delta_w, mc.EXP_THRESH),
name='bbox_width')
box_height = tf.identity(anchor_h *
util.safe_exp(delta_h, mc.EXP_THRESH),
name='bbox_height')
self._activation_summary(delta_x, 'delta_x')
self._activation_summary(delta_y, 'delta_y')
self._activation_summary(delta_w, 'delta_w')
self._activation_summary(delta_h, 'delta_h')
self._activation_summary(box_center_x, 'bbox_cx')
self._activation_summary(box_center_y, 'bbox_cy')
self._activation_summary(box_width, 'bbox_width')
self._activation_summary(box_height, 'bbox_height')
with tf.variable_scope('trimming'):
xmins, ymins, xmaxs, ymaxs = util.bbox_transform(
[box_center_x, box_center_y, box_width, box_height])
# The max x position is mc.IMAGE_WIDTH - 1 since we use zero-based
# pixels. Same for y.
xmins = tf.minimum(tf.maximum(0.0, xmins),
mc.IMAGE_WIDTH - 1.0,
name='bbox_xmin')
self._activation_summary(xmins, 'box_xmin')
ymins = tf.minimum(tf.maximum(0.0, ymins),
mc.IMAGE_HEIGHT - 1.0,
name='bbox_ymin')
self._activation_summary(ymins, 'box_ymin')
xmaxs = tf.maximum(tf.minimum(mc.IMAGE_WIDTH - 1.0, xmaxs),
0.0,
name='bbox_xmax')
self._activation_summary(xmaxs, 'box_xmax')
ymaxs = tf.maximum(tf.minimum(mc.IMAGE_HEIGHT - 1.0, ymaxs),
0.0,
name='bbox_ymax')
self._activation_summary(ymaxs, 'box_ymax')
self.det_boxes = tf.transpose(tf.stack(
util.bbox_transform_inv([xmins, ymins, xmaxs, ymaxs])),
(1, 2, 0),
name='bbox')
with tf.variable_scope('IOU'):
def _tensor_iou(box1, box2):
with tf.variable_scope('intersection'):
xmin = tf.maximum(box1[0], box2[0], name='xmin')
ymin = tf.maximum(box1[1], box2[1], name='ymin')
xmax = tf.minimum(box1[2], box2[2], name='xmax')
ymax = tf.minimum(box1[3], box2[3], name='ymax')
w = tf.maximum(0.0, xmax - xmin, name='inter_w')
h = tf.maximum(0.0, ymax - ymin, name='inter_h')
intersection = tf.multiply(w, h, name='intersection')
with tf.variable_scope('union'):
w1 = tf.subtract(box1[2], box1[0], name='w1')
h1 = tf.subtract(box1[3], box1[1], name='h1')
w2 = tf.subtract(box2[2], box2[0], name='w2')
h2 = tf.subtract(box2[3], box2[1], name='h2')
union = w1 * h1 + w2 * h2 - intersection
return intersection/(union+mc.EPSILON) \
* tf.reshape(self.input_mask, [mc.BATCH_SIZE, mc.ANCHORS])
self.ious = self.ious.assign(
_tensor_iou(
util.bbox_transform(tf.unstack(self.det_boxes, axis=2)),
util.bbox_transform(tf.unstack(self.box_input, axis=2))))
self._activation_summary(self.ious, 'conf_score')
with tf.variable_scope('probability') as scope:
self._activation_summary(self.pred_class_probs, 'class_probs')
probs = tf.multiply(self.pred_class_probs,
tf.reshape(self.pred_conf,
[mc.BATCH_SIZE, mc.ANCHORS, 1]),
name='final_class_prob')
self._activation_summary(probs, 'final_class_prob')
self.det_probs = tf.reduce_max(probs, 2, name='score')
self.det_class = tf.argmax(probs, 2, name='class_idx')
def _define_bbox(pred_bbox_delta, ANCHOR_BOX):
delta_x, delta_y, delta_w, delta_h = tf.unstack(
pred_bbox_delta, axis=2)
# set_anchors(mc, scale)
anchor_x = ANCHOR_BOX[:, 0]
anchor_y = ANCHOR_BOX[:, 1]
anchor_w = ANCHOR_BOX[:, 2]
anchor_h = ANCHOR_BOX[:, 3]
box_center_x = tf.identity(anchor_x + delta_x * anchor_w,
name='bbox_cx')
box_center_y = tf.identity(anchor_y + delta_y * anchor_h,
name='bbox_cy')
box_width = tf.identity(
anchor_w * util.safe_exp(delta_w, mc.EXP_THRESH),
name='bbox_width')
box_height = tf.identity(
anchor_h * util.safe_exp(delta_h, mc.EXP_THRESH),
name='bbox_height')
self._activation_summary(delta_x, 'delta_x')
self._activation_summary(delta_y, 'delta_y')
self._activation_summary(delta_w, 'delta_w')
self._activation_summary(delta_h, 'delta_h')
self._activation_summary(box_center_x, 'bbox_cx')
self._activation_summary(box_center_y, 'bbox_cy')
self._activation_summary(box_width, 'bbox_width')
self._activation_summary(box_height, 'bbox_height')
with tf.variable_scope('trimming'):
xmins, ymins, xmaxs, ymaxs = util.bbox_transform([
box_center_x, box_center_y, box_width, box_height
])
# The max x position is mc.IMAGE_WIDTH - 1 since we use zero-based
# pixels. Same for y.
xmins = tf.minimum(tf.maximum(0.0, xmins),
mc.IMAGE_WIDTH - 1.0,
name='bbox_xmin')
self._activation_summary(xmins, 'box_xmin')
ymins = tf.minimum(tf.maximum(0.0, ymins),
mc.IMAGE_HEIGHT - 1.0,
name='bbox_ymin')
self._activation_summary(ymins, 'box_ymin')
xmaxs = tf.maximum(tf.minimum(mc.IMAGE_WIDTH - 1.0,
xmaxs),
0.0,
name='bbox_xmax')
self._activation_summary(xmaxs, 'box_xmax')
ymaxs = tf.maximum(tf.minimum(mc.IMAGE_HEIGHT - 1.0,
ymaxs),
0.0,
name='bbox_ymax')
self._activation_summary(ymaxs, 'box_ymax')
det_boxes = tf.transpose(tf.stack(
util.bbox_transform_inv(
[xmins, ymins, xmaxs, ymaxs])), (1, 2, 0),
name='bbox')
return det_boxes
def _add_interpretation_graph(self):
"""Interpret NN output."""
mc = self.mc
with tf.variable_scope('interpret_output') as scope:
preds = self.preds
# probability
num_class_probs = mc.ANCHOR_PER_GRID * mc.CLASSES
self.pred_class_probs = tf.reshape(
tf.nn.softmax(
tf.reshape(preds[:, :, :, :num_class_probs],
[-1, mc.CLASSES])),
[mc.BATCH_SIZE, mc.ANCHORS, mc.CLASSES],
name='pred_class_probs')
# confidence
num_confidence_scores = mc.ANCHOR_PER_GRID + num_class_probs
self.pred_conf = tf.sigmoid(tf.reshape(
preds[:, :, :, num_class_probs:num_confidence_scores],
[mc.BATCH_SIZE, mc.ANCHORS]),
name='pred_confidence_score')
# bbox_delta
self.pred_box_delta = tf.reshape(preds[:, :, :,
num_confidence_scores:],
[mc.BATCH_SIZE, mc.ANCHORS, 4],
name='bbox_delta')
# number of objects. Used to normalize bbox and classification loss
# self.num_objects = tf.reduce_sum(self.input_mask, name='num_objects')
self.num_objects = tf.cast(
tf.size(self.box_input["image/object/bbox/xmin"].values),
tf.float32)
with tf.variable_scope('bbox') as scope:
with tf.variable_scope('stretching'):
delta_x, delta_y, delta_w, delta_h = tf.unstack(
self.pred_box_delta, axis=2)
anchor_x = mc.ANCHOR_BOX[:, 0]
anchor_y = mc.ANCHOR_BOX[:, 1]
anchor_w = mc.ANCHOR_BOX[:, 2]
anchor_h = mc.ANCHOR_BOX[:, 3]
box_center_x = tf.identity(anchor_x + delta_x * anchor_w,
name='bbox_cx')
box_center_y = tf.identity(anchor_y + delta_y * anchor_h,
name='bbox_cy')
box_width = tf.identity(anchor_w *
util.safe_exp(delta_w, mc.EXP_THRESH),
name='bbox_width')
box_height = tf.identity(anchor_h *
util.safe_exp(delta_h, mc.EXP_THRESH),
name='bbox_height')
self._activation_summary(delta_x, 'delta_x')
self._activation_summary(delta_y, 'delta_y')
self._activation_summary(delta_w, 'delta_w')
self._activation_summary(delta_h, 'delta_h')
self._activation_summary(box_center_x, 'bbox_cx')
self._activation_summary(box_center_y, 'bbox_cy')
self._activation_summary(box_width, 'bbox_width')
self._activation_summary(box_height, 'bbox_height')
with tf.variable_scope('trimming'):
xmins, ymins, xmaxs, ymaxs = util.bbox_transform(
[box_center_x, box_center_y, box_width, box_height])
# The max x position is mc.IMAGE_WIDTH - 1 since we use zero-based
# pixels. Same for y.
xmins = tf.minimum(
tf.maximum(0.0, xmins),
mc.IMAGE_WIDTH - 1.0,
name='bbox_xmin') # shape = [mc.BATCH_SIZE, mc.ANCHORS]
self._activation_summary(xmins, 'box_xmin')
ymins = tf.minimum(
tf.maximum(0.0, ymins),
mc.IMAGE_HEIGHT - 1.0,
name='bbox_ymin') # shape = [mc.BATCH_SIZE, mc.ANCHORS]
self._activation_summary(ymins, 'box_ymin')
xmaxs = tf.maximum(
tf.minimum(mc.IMAGE_WIDTH - 1.0, xmaxs),
0.0,
name='bbox_xmax') # shape = [mc.BATCH_SIZE, mc.ANCHORS]
self._activation_summary(xmaxs, 'box_xmax')
ymaxs = tf.maximum(
tf.minimum(mc.IMAGE_HEIGHT - 1.0, ymaxs),
0.0,
name='bbox_ymax') # shape = [mc.BATCH_SIZE, mc.ANCHORS]
self._activation_summary(ymaxs, 'box_ymax')
self.det_boxes = {
"xmins": xmins,
"ymins": ymins,
"xmaxs": xmaxs,
"ymaxs": ymaxs
}
with tf.name_scope('IOU'):
def _tensor_iou(box1, box2):
with tf.name_scope('intersection'):
xmin = tf.maximum(box1["xmin"], box2["xmin"], name='xmin')
ymin = tf.maximum(box1["ymin"], box2["ymin"], name='ymin')
xmax = tf.minimum(box1["xmax"], box2["xmax"], name='xmax')
ymax = tf.minimum(box1["ymax"], box2["ymax"], name='ymax')
w = tf.maximum(0.0, xmax - xmin, name='inter_w')
h = tf.maximum(0.0, ymax - ymin, name='inter_h')
intersection = tf.multiply(w, h, name='intersection')
with tf.name_scope('union'):
w1 = tf.subtract(box1["xmax"], box1["xmin"], name='w1')
h1 = tf.subtract(box1["ymax"], box1["ymin"], name='h1')
w2 = tf.subtract(box2["xmax"], box2["xmin"], name='w2')
h2 = tf.subtract(box2["ymax"], box2["ymin"], name='h2')
union = tf.cast(w1 * h1 + w2 * h2 - intersection,
dtype=tf.float32)
return tf.truediv(
tf.cast(intersection, dtype=tf.float32),
union + tf.constant(mc.EPSILON, dtype=tf.float32))
mini_ious_values = _tensor_iou(
{
"xmin":
tf.cast(tf.gather_nd(xmins, self.paired_aidx_values),
tf.float32),
"ymin":
tf.cast(tf.gather_nd(ymins, self.paired_aidx_values),
tf.float32),
"xmax":
tf.cast(tf.gather_nd(xmaxs, self.paired_aidx_values),
tf.float32),
"ymax":
tf.cast(tf.gather_nd(ymaxs, self.paired_aidx_values),
tf.float32)
}, # predicted boxes
{
"xmin":
tf.cast(self.box_input["image/object/bbox/xmin"].values,
tf.float32),
"ymin":
tf.cast(self.box_input["image/object/bbox/ymin"].values,
tf.float32),
"xmax":
tf.cast(self.box_input["image/object/bbox/xmax"].values,
tf.float32),
"ymax":
tf.cast(self.box_input["image/object/bbox/ymax"].values,
tf.float32)
}) # input boxes
# after computing the ious of the responsible boxes,
# put the values to a large plane containing all anchors which are responsible and those which are not
self._ious = tf.scatter_nd(self.paired_aidx_values,
mini_ious_values,
[mc.BATCH_SIZE, mc.ANCHORS])
self._activation_summary(self._ious, 'conf_score')
with tf.variable_scope('probability') as scope:
self._activation_summary(self.pred_class_probs, 'class_probs')
probs = tf.multiply(self.pred_class_probs,
tf.reshape(self.pred_conf,
[mc.BATCH_SIZE, mc.ANCHORS, 1]),
name='final_class_prob')
self._activation_summary(probs, 'final_class_prob')
self.det_probs = tf.reduce_max(probs, axis=2, name='score')
self.det_class = tf.argmax(probs, axis=2, name='class_idx')
self._activation_summary(
tf.gather_nd(self.det_class, self.paired_aidx_values),
'detected_classes')
# get prediction boxes
self.prediction_boxes, self.score,\
self.cls_idx_per_img, self.filter_summaries = self.filter_prediction()
def _add_interpretation_graph(self):
"""Interpret NN output."""
mc = self.mc
with tf.variable_scope('interpret_output') as scope:
preds = self.preds
# probability
num_class_probs = mc.ANCHOR_PER_GRID * mc.CLASSES
if mc.CLASSES == 1:
self.pred_class_probs = tf.reshape(
tf.sigmoid(
tf.reshape(preds[:, :, :, :num_class_probs],
[-1, mc.CLASSES])),
[mc.BATCH_SIZE, mc.ANCHORS, mc.CLASSES],
name='pred_class_probs')
else:
self.pred_class_probs = tf.reshape(
tf.nn.softmax(
tf.reshape(preds[:, :, :, :num_class_probs],
[-1, mc.CLASSES])),
[mc.BATCH_SIZE, mc.ANCHORS, mc.CLASSES],
name='pred_class_probs')
# bbox_delta
self.pred_box_delta = tf.reshape(preds[:, :, :, num_class_probs:],
[mc.BATCH_SIZE, mc.ANCHORS, 4],
name='bbox_delta')
with tf.variable_scope('bbox') as scope:
with tf.variable_scope('stretching'):
delta_x, delta_y, delta_w, delta_h = tf.unstack(
self.pred_box_delta, axis=2)
anchor_x = mc.ANCHOR_BOX[:, 0]
anchor_y = mc.ANCHOR_BOX[:, 1]
anchor_w = mc.ANCHOR_BOX[:, 2]
anchor_h = mc.ANCHOR_BOX[:, 3]
box_center_x = tf.identity(anchor_x + delta_x * anchor_w,
name='bbox_cx')
box_center_y = tf.identity(anchor_y + delta_y * anchor_h,
name='bbox_cy')
box_width = tf.identity(anchor_w *
util.safe_exp(delta_w, mc.EXP_THRESH),
name='bbox_width')
box_height = tf.identity(anchor_h *
util.safe_exp(delta_h, mc.EXP_THRESH),
name='bbox_height')
self._activation_summary(delta_x, 'delta_x')
self._activation_summary(delta_y, 'delta_y')
self._activation_summary(delta_w, 'delta_w')
self._activation_summary(delta_h, 'delta_h')
self._activation_summary(box_center_x, 'bbox_cx')
self._activation_summary(box_center_y, 'bbox_cy')
self._activation_summary(box_width, 'bbox_width')
self._activation_summary(box_height, 'bbox_height')
with tf.variable_scope('trimming'):
xmins, ymins, xmaxs, ymaxs = util.bbox_transform(
[box_center_x, box_center_y, box_width, box_height])
# The max x position is mc.IMAGE_WIDTH - 1 since we use zero-based
# pixels. Same for y.
xmins = tf.minimum(tf.maximum(0.0, xmins),
mc.IMAGE_WIDTH - 1.0,
name='bbox_xmin')
self._activation_summary(xmins, 'box_xmin')
ymins = tf.minimum(tf.maximum(0.0, ymins),
mc.IMAGE_HEIGHT - 1.0,
name='bbox_ymin')
self._activation_summary(ymins, 'box_ymin')
xmaxs = tf.maximum(tf.minimum(mc.IMAGE_WIDTH - 1.0, xmaxs),
0.0,
name='bbox_xmax')
self._activation_summary(xmaxs, 'box_xmax')
ymaxs = tf.maximum(tf.minimum(mc.IMAGE_HEIGHT - 1.0, ymaxs),
0.0,
name='bbox_ymax')
self._activation_summary(ymaxs, 'box_ymax')
self.det_boxes = tf.transpose(tf.stack(
util.bbox_transform_inv([xmins, ymins, xmaxs, ymaxs])),
(1, 2, 0),
name='bbox')
with tf.variable_scope('probability') as scope:
self._activation_summary(self.pred_class_probs, 'class_probs')
probs = self.pred_class_probs
self.det_probs = tf.reduce_max(probs, 2, name='score')
self.det_class = tf.argmax(probs, 2, name='class_idx')
def _add_interpretation_graph(self):
"""Interpret NN output."""
mc = self.mc
with tf.variable_scope('interpret_output') as scope:
preds = self.preds
# probability
num_class_probs = mc.ANCHOR_PER_GRID * mc.CLASSES
self.pred_class_probs = tf.reshape(
tf.nn.softmax(
tf.reshape(preds[:, :, :, :num_class_probs],
[-1, mc.CLASSES])),
[mc.BATCH_SIZE, mc.ANCHORS, mc.CLASSES],
name='pred_class_probs')
# confidence
num_confidence_scores = mc.ANCHOR_PER_GRID + num_class_probs
self.pred_conf = tf.sigmoid(tf.reshape(
preds[:, :, :, num_class_probs:num_confidence_scores],
[mc.BATCH_SIZE, mc.ANCHORS]),
name='pred_confidence_score')
# bbox_delta
self.pred_box_delta = tf.reshape(
preds[:, :, :, num_confidence_scores:],
[mc.BATCH_SIZE, mc.ANCHORS, self.num_mask_params],
name='bbox_delta')
# number of object. Used to normalize bbox and classification loss
self.num_objects = tf.reduce_sum(self.input_mask,
name='num_objects')
with tf.variable_scope('bbox') as scope:
with tf.variable_scope('stretching'):
if self.mc.EIGHT_POINT_REGRESSION:
if mc.ENCODING_TYPE == 'normal':
delta_x, delta_y, delta_w, delta_h, \
delta_of1, delta_of2, delta_of3, delta_of4 = tf.unstack(
self.pred_box_delta, axis=2)
else:
delta_xmin, delta_ymin, delta_xmax, delta_ymax, \
delta_of1, delta_of2, delta_of3, delta_of4 = tf.unstack(
self.pred_box_delta, axis=2)
else:
if mc.ENCODING_TYPE == 'normal':
delta_x, delta_y, delta_w, delta_h = tf.unstack(
self.pred_box_delta, axis=2)
else:
delta_xmin, delta_ymin, delta_xmax, delta_ymax = tf.unstack(
self.pred_box_delta, axis=2)
anchor_x = mc.ANCHOR_BOX[:, 0]
anchor_y = mc.ANCHOR_BOX[:, 1]
anchor_w = mc.ANCHOR_BOX[:, 2]
anchor_h = mc.ANCHOR_BOX[:, 3]
if mc.ENCODING_TYPE == 'asymmetric_linear':
xmins_a, ymins_a, xmaxs_a, ymaxs_a = util.bbox_transform(
np.transpose(mc.ANCHOR_BOX))
xmins = tf.identity(xmins_a + delta_xmin * anchor_w,
name='bbox_xmin_uncropped')
ymins = tf.identity(ymins_a + delta_ymin * anchor_h,
name='bbox_ymin_uncropped')
xmaxs = tf.identity(xmaxs_a + delta_xmax * anchor_w,
name='bbox_xmax_uncropped')
ymaxs = tf.identity(ymaxs_a + delta_ymax * anchor_h,
name='bbox_ymax_uncropped')
box_center_x, box_center_y, box_width, box_height = util.bbox_transform_inv(
[xmins, ymins, xmaxs, ymaxs])
self._activation_summary(delta_xmin, 'delta_xmin')
self._activation_summary(delta_ymin, 'delta_ymin')
self._activation_summary(delta_xmax, 'delta_xmax')
self._activation_summary(delta_ymax, 'delta_ymax')
elif mc.ENCODING_TYPE == 'asymmetric_log':
EPSILON = 0.5
xmins = tf.identity(
anchor_x -
(anchor_w *
(util.safe_exp(delta_xmin, mc.EXP_THRESH) - EPSILON)),
name='bbox_xmin_uncropped')
ymins = tf.identity(
anchor_y -
(anchor_h *
(util.safe_exp(delta_ymin, mc.EXP_THRESH) - EPSILON)),
name='bbox_ymin_uncropped')
xmaxs = tf.identity(
anchor_x +
(anchor_w *
(util.safe_exp(delta_xmax, mc.EXP_THRESH) - EPSILON)),
name='bbox_xmax_uncropped')
ymaxs = tf.identity(
anchor_y +
(anchor_h *
(util.safe_exp(delta_ymax, mc.EXP_THRESH) - EPSILON)),
name='bbox_ymax_uncropped')
box_center_x, box_center_y, box_width, box_height = util.bbox_transform_inv(
[xmins, ymins, xmaxs, ymaxs])
self._activation_summary(delta_xmin, 'delta_xmin')
self._activation_summary(delta_ymin, 'delta_ymin')
self._activation_summary(delta_xmax, 'delta_xmax')
self._activation_summary(delta_ymax, 'delta_ymax')
else:
box_center_x = tf.identity(anchor_x + delta_x * anchor_w,
name='bbox_cx')
box_center_y = tf.identity(anchor_y + delta_y * anchor_h,
name='bbox_cy')
box_width = tf.identity(
anchor_w * util.safe_exp(delta_w, mc.EXP_THRESH),
name='bbox_width')
box_height = tf.identity(
anchor_h * util.safe_exp(delta_h, mc.EXP_THRESH),
name='bbox_height')
self._activation_summary(delta_x, 'delta_x')
self._activation_summary(delta_y, 'delta_y')
self._activation_summary(delta_w, 'delta_w')
self._activation_summary(delta_h, 'delta_h')
self._activation_summary(box_center_x, 'bbox_cx')
self._activation_summary(box_center_y, 'bbox_cy')
self._activation_summary(box_width, 'bbox_width')
self._activation_summary(box_height, 'bbox_height')
if self.mc.EIGHT_POINT_REGRESSION:
EPSILON = 1e-8
anchor_diag = (mc.ANCHOR_BOX[:, 2]**2 +
mc.ANCHOR_BOX[:, 3]**2)**(0.5)
box_of1 = tf.identity(
(anchor_diag * util.safe_exp(delta_of1, mc.EXP_THRESH))
- EPSILON,
name='bbox_of1')
box_of2 = tf.identity(
(anchor_diag * util.safe_exp(delta_of2, mc.EXP_THRESH))
- EPSILON,
name='bbox_of2')
box_of3 = tf.identity(
(anchor_diag * util.safe_exp(delta_of3, mc.EXP_THRESH))
- EPSILON,
name='bbox_of3')
box_of4 = tf.identity(
(anchor_diag * util.safe_exp(delta_of4, mc.EXP_THRESH))
- EPSILON,
name='bbox_of4')
self._activation_summary(delta_of1, 'delta_of1')
self._activation_summary(delta_of2, 'delta_of2')
self._activation_summary(delta_of3, 'delta_of3')
self._activation_summary(delta_of4, 'delta_of4')
self._activation_summary(box_of1, 'box_of1')
self._activation_summary(box_of2, 'box_of2')
self._activation_summary(box_of3, 'box_of3')
self._activation_summary(box_of4, 'box_of4')
with tf.variable_scope('trimming'):
if self.mc.EIGHT_POINT_REGRESSION:
xmins, ymins, xmaxs, ymaxs, box_of1, box_of2, box_of3, box_of4 = util.bbox_transform2(
[
box_center_x, box_center_y, box_width, box_height,
box_of1, box_of2, box_of3, box_of4
])
else:
if mc.ENCODING_TYPE == 'normal':
xmins, ymins, xmaxs, ymaxs = util.bbox_transform([
box_center_x, box_center_y, box_width, box_height
])
if self.mc.EIGHT_POINT_REGRESSION:
self.det_boxes_uncropped = tf.transpose(
tf.stack(
util.bbox_transform_inv2([
xmins, ymins, xmaxs, ymaxs, box_of1, box_of2,
box_of3, box_of4
])), (1, 2, 0),
name='bbox_uncropped')
else:
self.det_boxes_uncropped = tf.transpose(
tf.stack(
util.bbox_transform_inv(
[xmins, ymins, xmaxs, ymaxs])), (1, 2, 0),
name='bbox_uncropped')
# The max x position is mc.IMAGE_WIDTH - 1 since we use zero-based
# pixels. Same for y.
xmins = tf.minimum(tf.maximum(0.0, xmins),
mc.IMAGE_WIDTH - 1.0,
name='bbox_xmin')
self._activation_summary(xmins, 'box_xmin')
ymins = tf.minimum(tf.maximum(0.0, ymins),
mc.IMAGE_HEIGHT - 1.0,
name='bbox_ymin')
self._activation_summary(ymins, 'box_ymin')
xmaxs = tf.maximum(tf.minimum(mc.IMAGE_WIDTH - 1.0, xmaxs),
0.0,
name='bbox_xmax')
self._activation_summary(xmaxs, 'box_xmax')
ymaxs = tf.maximum(tf.minimum(mc.IMAGE_HEIGHT - 1.0, ymaxs),
0.0,
name='bbox_ymax')
self._activation_summary(ymaxs, 'box_ymax')
if self.mc.EIGHT_POINT_REGRESSION:
self.det_boxes = tf.transpose(tf.stack(
util.bbox_transform_inv2([
xmins, ymins, xmaxs, ymaxs, box_of1, box_of2,
box_of3, box_of4
])), (1, 2, 0),
name='bbox')
else:
self.det_boxes = tf.transpose(tf.stack(
util.bbox_transform_inv([xmins, ymins, xmaxs, ymaxs])),
(1, 2, 0),
name='bbox')
with tf.variable_scope('IOU'):
def _tensor_iou(box1, box2):
with tf.variable_scope('intersection'):
xmin = tf.maximum(box1[0], box2[0], name='xmin')
ymin = tf.maximum(box1[1], box2[1], name='ymin')
xmax = tf.minimum(box1[2], box2[2], name='xmax')
ymax = tf.minimum(box1[3], box2[3], name='ymax')
w = tf.maximum(0.0, xmax - xmin, name='inter_w')
h = tf.maximum(0.0, ymax - ymin, name='inter_h')
intersection = tf.multiply(w, h, name='intersection')
with tf.variable_scope('union'):
w1 = tf.subtract(box1[2], box1[0], name='w1')
h1 = tf.subtract(box1[3], box1[1], name='h1')
w2 = tf.subtract(box2[2], box2[0], name='w2')
h2 = tf.subtract(box2[3], box2[1], name='h2')
union = w1 * h1 + w2 * h2 - intersection
return intersection/(union+mc.EPSILON) \
* tf.reshape(self.input_mask, [mc.BATCH_SIZE, mc.ANCHORS])
if self.mc.EIGHT_POINT_REGRESSION:
tensor_det_boxes = util.bbox_transform2(
tf.unstack(self.det_boxes, axis=2))
tensor_input_boxes = util.bbox_transform2(
tf.unstack(self.box_input, axis=2))
else:
tensor_det_boxes = util.bbox_transform(
tf.unstack(self.det_boxes, axis=2))
tensor_input_boxes = util.bbox_transform(
tf.unstack(self.box_input, axis=2))
self.ious = self.ious.assign(
_tensor_iou(tensor_det_boxes, tensor_input_boxes))
self._activation_summary(self.ious, 'conf_score')
with tf.variable_scope('probability') as scope:
self._activation_summary(self.pred_class_probs, 'class_probs')
probs = tf.multiply(self.pred_class_probs,
tf.reshape(self.pred_conf,
[mc.BATCH_SIZE, mc.ANCHORS, 1]),
name='final_class_prob')
self._activation_summary(probs, 'final_class_prob')
self.det_probs = tf.reduce_max(probs, 2, name='score')
self.det_class = tf.argmax(probs, 2, name='class_idx')
