def loss_without_regularization(self, y_true, y_pred):
#handle for config
mc = self.config
#slice y_true
input_mask = y_true[:, :, 0]
input_mask = K.expand_dims(input_mask, axis=-1)
box_input = y_true[:, :, 1:5]
box_delta_input = y_true[:, :, 5:9]
labels = y_true[:, :, 9:]
#number of objects. Used to normalize bbox and classification loss
num_objects = K.sum(input_mask)
#before computing the losses we need to slice the network outputs
pred_class_probs, pred_conf, pred_box_delta = ut.slice_predictions(
y_pred, mc)
#compute boxes
det_boxes = ut.boxes_from_deltas(pred_box_delta, mc)
#again unstack is not avaible in pure keras backend
unstacked_boxes_pred = []
unstacked_boxes_input = []
for i in range(4):
unstacked_boxes_pred.append(det_boxes[:, :, i])
unstacked_boxes_input.append(box_input[:, :, i])
#compute the ious
ious = ut.tensor_iou(ut.bbox_transform(unstacked_boxes_pred),
ut.bbox_transform(unstacked_boxes_input),
input_mask, mc)
#compute class loss
class_loss = K.sum(labels * (-K.log(pred_class_probs + mc.EPSILON)) +
(1 - labels) *
(-K.log(1 - pred_class_probs + mc.EPSILON)) *
input_mask * mc.LOSS_COEF_CLASS) / num_objects
#bounding box loss
bbox_loss = (K.sum(
mc.LOSS_COEF_BBOX * K.square(input_mask *
(pred_box_delta - box_delta_input))) /
num_objects)
#reshape input for correct broadcasting
input_mask = K.reshape(input_mask, [mc.BATCH_SIZE, mc.ANCHORS_NO])
#confidence score loss
conf_loss = K.mean(
K.sum(K.square((ious - pred_conf)) *
(input_mask * mc.LOSS_COEF_CONF_POS / num_objects +
(1 - input_mask) * mc.LOSS_COEF_CONF_NEG /
(mc.ANCHORS_NO - num_objects)),
axis=[1]), )
# add above losses
total_loss = class_loss + conf_loss + bbox_loss
return total_loss
def conf_loss(self, y_true, y_pred):
#handle for config
mc = self.config
#calculate non padded entries
n_outputs = mc.CLASS_NO + 1 + 4
#slice and reshape network output
y_pred = y_pred[:, :, 0:n_outputs]
y_pred = K.reshape(
y_pred, (mc.BATCH_SIZE, mc.ANCHOR_HEIGHT, mc.ANCHOR_WIDTH, -1))
#slice y_true
input_mask = y_true[:, :, 0]
input_mask = K.expand_dims(input_mask, axis=-1)
box_input = y_true[:, :, 1:5]
#number of objects. Used to normalize bbox and classification loss
num_objects = K.sum(input_mask)
#number of class probabilities, n classes for each anchor
num_class_probs = mc.ANCHOR_PER_GRID * mc.CLASS_NO
#number of confidence scores, one for each anchor + class probs
num_confidence_scores = mc.ANCHOR_PER_GRID + num_class_probs
#slice the confidence scores and put them trough a sigmoid for probabilities
pred_conf = K.sigmoid(
K.reshape(y_pred[:, :, :, num_class_probs:num_confidence_scores],
[mc.BATCH_SIZE, mc.ANCHORS_NO]))
#slice remaining bounding box_deltas
pred_box_delta = K.reshape(y_pred[:, :, :, num_confidence_scores:],
[mc.BATCH_SIZE, mc.ANCHORS_NO, 4])
#compute boxes
det_boxes = ut.boxes_from_deltas(pred_box_delta, mc)
#again unstack is not avaible in pure keras backend
unstacked_boxes_pred = []
unstacked_boxes_input = []
for i in range(4):
unstacked_boxes_pred.append(det_boxes[:, :, i])
unstacked_boxes_input.append(box_input[:, :, i])
#compute the ious
ious = ut.tensor_iou(ut.bbox_transform(unstacked_boxes_pred),
ut.bbox_transform(unstacked_boxes_input),
input_mask, mc)
#reshape input for correct broadcasting
input_mask = K.reshape(input_mask, [mc.BATCH_SIZE, mc.ANCHORS_NO])
#confidence score loss
conf_loss = K.mean(
K.sum(K.square((ious - pred_conf)) *
(input_mask * mc.LOSS_COEF_CONF_POS / num_objects +
(1 - input_mask) * mc.LOSS_COEF_CONF_NEG /
(mc.ANCHORS_NO - num_objects)),
axis=[1]), )
return conf_loss