Ejemplo n.º 1
0
 def new_update(x, new_x):
     if is_one_of(x, params) and self._do_layer_adaptation(x):
         dx = new_x - x
         lr_t = K.clip(self.learning_rate, K.epsilon(), 1e10)
         x_norm = tf.norm(x)
         g_norm = tf.norm(dx / lr_t)
         ratio = K.switch(
             x_norm > 0.0,
             K.switch(g_norm > K.epsilon(), x_norm / g_norm, 1.0),
             1.0)
         new_x = x + dx * ratio
     return old_update(x, new_x)
Ejemplo n.º 2
0
 def new_update(x, new_x):
     if x is var and self._do_layer_adaptation(x):
         dx = new_x - x
         lr_t = self._decayed_lr(x.dtype.base_dtype)
         lr_t = K.clip(lr_t, K.epsilon(), 1e10)
         x_norm = tf.norm(x)
         g_norm = tf.norm(dx / lr_t)
         ratio = K.switch(
             x_norm > 0.0,
             K.switch(g_norm > K.epsilon(), x_norm / g_norm, 1.0),
             1.0)
         new_x = x + dx * ratio
     return old_update(x, new_x)
Ejemplo n.º 3
0
 def compute_position_ids(self, inputs):
     q, v = inputs
     # 计算位置差
     q_idxs = K.arange(0, K.shape(q)[1], dtype='int32')
     q_idxs = K.expand_dims(q_idxs, 1)
     v_idxs = K.arange(0, K.shape(v)[1], dtype='int32')
     v_idxs = K.expand_dims(v_idxs, 0)
     pos_ids = v_idxs - q_idxs
     # 后处理操作
     max_position = (self.input_dim - 1) // 2
     pos_ids = K.clip(pos_ids, -max_position, max_position)
     pos_ids = pos_ids + max_position
     return pos_ids