def calc_loss(logits: tf.Tensor, caps_out: tf.Tensor, x: tf.Tensor, y: tf.Tensor, decoded: tf.Tensor):
with tf.variable_scope('calc_loss'):
# margin loss 中调节上margin和下margind的权重
lambda_val = 0.5
# 上margin与下margin的参数值
m_plus = 0.95
m_minus = 0.05
max_l = tf.square(tf.maximum(0., m_plus-logits))
max_r = tf.square(tf.maximum(0., logits-m_minus))
margin_loss = tf.reduce_mean(tf.reduce_sum(y * max_l + lambda_val * (1. - y) * max_r, axis=-1))
orgin = tf.reshape(x, (x.shape[0], -1))
reconstruct_loss = 0.0005*tf.reduce_mean(tf.square(orgin-decoded))
total_loss = margin_loss+reconstruct_loss
return total_loss
def _setup_actor_critic_loss(self, actor, critic, num_actions):
actions_one_hot = tf.placeholder(tf.float32, [None, num_actions])
action_probability = tf.reduce_sum(actor * actions_one_hot, axis=1)
log_prob = tf.log(tf.maximum(action_probability, self._log_noise))
advantage = self._R - tf.stop_gradient(critic)
entropy = tf.reduce_sum(tf.log(tf.maximum(actor, self._log_noise)) * actor, axis=1)
actor_loss = -(tf.reduce_sum((log_prob * advantage), axis=0) + tf.reduce_sum((-1 * self._entropy_beta * entropy), axis=0))
critic_loss = tf.reduce_sum(tf.square(self._R - critic), axis=0)
loss = 0.5 * critic_loss + actor_loss
return loss, actions_one_hot
def tf_iou(pred_xy: tf.Tensor, pred_wh: tf.Tensor, vaild_xy: tf.Tensor,
vaild_wh: tf.Tensor) -> tf.Tensor:
""" calc the iou form pred box with vaild box
Parameters
----------
pred_xy : tf.Tensor
pred box shape = [out h, out w, anchor num, 2]
pred_wh : tf.Tensor
pred box shape = [out h, out w, anchor num, 2]
vaild_xy : tf.Tensor
vaild box shape = [? , 2]
vaild_wh : tf.Tensor
vaild box shape = [? , 2]
Returns
-------
tf.Tensor
iou value shape = [out h, out w, anchor num ,?]
"""
b1_xy = tf.expand_dims(pred_xy, -2)
b1_wh = tf.expand_dims(pred_wh, -2)
b1_wh_half = b1_wh / 2.
b1_mins = b1_xy - b1_wh_half
b1_maxes = b1_xy + b1_wh_half
b2_xy = tf.expand_dims(vaild_xy, 0)
b2_wh = tf.expand_dims(vaild_wh, 0)
b2_wh_half = b2_wh / 2.
b2_mins = b2_xy - b2_wh_half
b2_maxes = b2_xy + b2_wh_half
intersect_mins = tf.maximum(b1_mins, b2_mins)
intersect_maxes = tf.minimum(b1_maxes, b2_maxes)
intersect_wh = tf.maximum(intersect_maxes - intersect_mins, 0.)
intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
b1_area = b1_wh[..., 0] * b1_wh[..., 1]
b2_area = b2_wh[..., 0] * b2_wh[..., 1]
iou = intersect_area / (b1_area + b2_area - intersect_area)
return iou