Question

我正在使用Tensorflow并遇到此代码的问题：

def process_tree_tf(matrix, weights, idxs, name=None):

    with tf.name_scope(name, "process_tree", [tree, weights, idxs]).as scope():
         loop_index = tf.sub(tf.shape(matrix)[0], 1)
         loop_vars = loop_index, matrix, idxs, weights

         def loop_condition(loop_idx, *_):
             return tf.greater(loop_idx, 0)

         def loop_body(loop_idx, mat, idxs, weights):
             x = mat[loop_idx]
             w = weights
             bias = tf.Variable(tf.constant(0.1, [2], dtype=tf.float64)) # Here?

             ...
             return loop_idx-1, mat, idxs, weights

         return tf.while_loop(loop_condition, loop_body, loop_vars, name=scope)[1]

我以这种方式评估功能：

height = 2
width = 2
nodes = 4
matrix = np.ones((nodes, width+height))
weights = np.ones((width+height, width))/100
idxs = [0,0,1,2]
with tf.Session as sess():
    sess.run(tf.global_variables_initializer()) # Error Here!
    r = process_tree_tf(matrix, weights, idxs)
    print(r.eval())

我收到此错误：

InvalidArgumentError：节点＆＃39; process_tree_tf / Variable / Assign＆＃39;有来自不同帧的输入。输入＆＃39; process_tree_tf / Const_1＆＃39;在框架内＆＃39; process_tree_tf / process_tree_tf /＆＃39;。输入＆＃39; process_tree_tf / Variable＆＃39;在框架中＆＃39;
。

奇怪的是，如果我在jupyter笔记本中重新启动内核并再次运行，我会收到此错误：

FailedPreconditionError（参见上面的回溯）：尝试使用未初始化的值偏差 [[Node：bias / read = IdentityT = DT_FLOAT，_class = [＆＃34; loc：@ bias＆＃34;]，_ device =＆＃34; / job：localhost / replica：0 / task：0 / cpu：0＆＃34;]]

我尝试使用此代替： bias = tf.get_variable("bias", shape=[2], initializer=tf.constant_initializer(0.1))，但这也无效。

如果我忽略了一些显而易见的事情，我很抱歉，但如果有人能告诉我哪里出错了，我真的很感激。

非常感谢！

Answer 1

这实际上是TensorFlow tf.Variable中tf.while_loop()个对象的一个微妙问题。 TensorFlow变得混乱，因为您初始化变量的tf.constant()似乎是在循环内创建的值（即使它显然是循环不变的），但是所有变量都在环。最简单的解决方案是将变量的创建移到循环之外：

def process_tree_tf(matrix, weights, idxs, name=None):

    with tf.name_scope(name, "process_tree", [tree, weights, idxs]).as scope():
         loop_index = tf.sub(tf.shape(matrix)[0], 1)
         loop_vars = loop_index, matrix, idxs, weights

         # Define the bias variable outside the loop to avoid problems.
         bias = tf.Variable(tf.constant(0.1, [2], dtype=tf.float64)) 

         def loop_condition(loop_idx, *_):
             return tf.greater(loop_idx, 0)

         def loop_body(loop_idx, mat, idxs, weights):
             x = mat[loop_idx]
             w = weights

             # You can still refer to `bias` in here, and the loop body
             # will capture it appropriately.
             ...
             return loop_idx-1, mat, idxs, weights

         return tf.while_loop(loop_condition, loop_body, loop_vars, name=scope)[1]

（另一种可能的解决方案是在创建变量时使用tf.constant_initializer()而不是tf.constant()。）

Answer 2

您可以在biases内部初始化loop_body，如下所示：

 def loop_body(loop_idx, mat, idxs, weights):
     x = mat[loop_idx]
     w = weights
     bias = tf.get_variable(dtype=tf.float64,
                            shape=[2],
                            initializer=tf.constant_initializer(value=np.array([0.1,0.1]), dtype=tf.float64))

您说您曾经尝试过tf.get_variable和tf.constant_initializer，但我想知道您是否找到了另一个解决方案？

InvalidArgumentError：节点具有来自不同帧

2 个答案: