def __loss_per_scale(self, name, conv, pred, label, bboxes, stride):
with tf.name_scope(name):
conv_shape = tf.shape(conv)
batch_size = conv_shape[0]
output_size = conv_shape[1]
input_size = stride * output_size
conv = tf.reshape(conv,
(batch_size, output_size, output_size,
self.__gt_per_grid, 5 + self.__num_classes))
conv_raw_conf = conv[:, :, :, :, 4:5]
conv_raw_prob = conv[:, :, :, :, 5:]
pred_coor = pred[:, :, :, :, 0:4]
pred_conf = pred[:, :, :, :, 4:5]
label_coor = label[:, :, :, :, 0:4]
respond_bbox = label[:, :, :, :, 4:5]
label_prob = label[:, :, :, :, 5:-1]
label_mixw = label[:, :, :, :, -1:]
# 计算GIOU损失
GIOU = tools.GIOU(pred_coor, label_coor)
GIOU = GIOU[..., np.newaxis]
input_size = tf.cast(input_size, tf.float32)
bbox_wh = label_coor[..., 2:] - label_coor[..., :2]
bbox_loss_scale = 2.0 - 1.0 * bbox_wh[0] * bbox_wh[1] / (input_size
**2)
GIOU_loss = respond_bbox * bbox_loss_scale * (1.0 - GIOU)
# (2)计算confidence损失
iou = tools.iou_calc3(
pred_coor[:, :, :, :, np.newaxis, :],
bboxes[:, np.newaxis, np.newaxis, np.newaxis, :, :])
max_iou = tf.reduce_max(iou, axis=-1)
max_iou = max_iou[:, :, :, :, np.newaxis]
respond_bgd = (1.0 - respond_bbox) * tf.cast(
max_iou < self.__iou_loss_thresh, tf.float32)
conf_focal = self.__focal(respond_bbox, pred_conf)
conf_loss = conf_focal * (
respond_bbox * tf.nn.sigmoid_cross_entropy_with_logits(
labels=respond_bbox, logits=conv_raw_conf) +
respond_bgd * tf.nn.sigmoid_cross_entropy_with_logits(
labels=respond_bbox, logits=conv_raw_conf))
# (3)计算classes损失
prob_loss = respond_bbox * tf.nn.sigmoid_cross_entropy_with_logits(
labels=label_prob, logits=conv_raw_prob)
loss = tf.concat([GIOU_loss, conf_loss, prob_loss], axis=-1)
loss = loss * label_mixw
loss = tf.reduce_mean(tf.reduce_sum(loss, axis=[1, 2, 3, 4]))
return loss
def __loss_per_scale(self, name, conv, pred, label, bboxes, stride):
"""
:param name: loss的名字
:param conv: conv是yolo卷积层的原始输出
shape为(batch_size, output_size, output_size, anchor_per_scale * (5 + num_class))
:param pred: conv是yolo输出的预测bbox的信息(x, y, w, h, conf, prob)，
其中(x, y, w, h)的大小是相对于input_size的，如input_size=416，(x, y, w, h) = (120, 200, 50, 70)
shape为(batch_size, output_size, output_size, anchor_per_scale, 5 + num_class)
:param label: shape为(batch_size, output_size, output_size, anchor_per_scale, 6 + num_classes)
只有负责预测GT的对应位置的数据才为(xmin, ymin, xmax, ymax, 1, classes, mixup_weights),
其他位置的数据都为(0, 0, 0, 0, 0, 0..., 1)
:param bboxes: shape为(batch_size, max_bbox_per_scale, 4)，
存储的坐标为(xmin, ymin, xmax, ymax)
bboxes用于计算相应detector的预测框与该detector负责预测的所有bbox的IOU
:param anchors: 相应detector的anchors
:param stride: 相应detector的stride
"""
with tf.name_scope(name):
conv_shape = tf.shape(conv)
batch_size = conv_shape[0]
output_size = conv_shape[1]
input_size = stride * output_size
conv = tf.reshape(conv,
(batch_size, output_size, output_size,
self.__gt_per_grid, 5 + self.__num_classes))
conv_raw_conf = conv[..., 4:5]
conv_raw_prob = conv[..., 5:]
pred_coor = pred[..., 0:4]
pred_conf = pred[..., 4:5]
label_coor = label[..., 0:4]
respond_bbox = label[..., 4:5]
label_prob = label[..., 5:-1]
label_mixw = label[..., -1:]
# 计算GIOU损失
GIOU = tools.GIOU(pred_coor, label_coor)
GIOU = GIOU[..., np.newaxis]
input_size = tf.cast(input_size, tf.float32)
bbox_wh = label_coor[..., 2:] - label_coor[..., :2]
bbox_loss_scale = 2.0 - 1.0 * bbox_wh[..., 0:1] * bbox_wh[
..., 1:2] / (input_size**2)
GIOU_loss = respond_bbox * bbox_loss_scale * (1.0 - GIOU)
# (2)计算confidence损失
iou = tools.iou_calc3(
pred_coor[:, :, :, :, np.newaxis, :],
bboxes[:, np.newaxis, np.newaxis, np.newaxis, :, :])
max_iou = tf.reduce_max(iou, axis=-1)
max_iou = max_iou[..., np.newaxis]
respond_bgd = (1.0 - respond_bbox) * tf.cast(
max_iou < self.__iou_loss_thresh, tf.float32)
conf_focal = self.__focal(respond_bbox, pred_conf)
conf_loss = conf_focal * (
respond_bbox * tf.nn.sigmoid_cross_entropy_with_logits(
labels=respond_bbox, logits=conv_raw_conf) +
respond_bgd * tf.nn.sigmoid_cross_entropy_with_logits(
labels=respond_bbox, logits=conv_raw_conf))
# (3)计算classes损失
prob_loss = respond_bbox * tf.nn.sigmoid_cross_entropy_with_logits(
labels=label_prob, logits=conv_raw_prob)
loss = tf.concat([GIOU_loss, conf_loss, prob_loss], axis=-1)
loss = loss * label_mixw
loss = tf.reduce_mean(tf.reduce_sum(loss, axis=[1, 2, 3, 4]))
return loss