Python 为什么它仍然这么说；FailedPremissionError:尝试使用未初始化的值“；

我想在做tensorboard时创建一些层。我定义了所有变量，并将名称放入每个变量中。当然，我使用了

init=tf.global\u variables\u initializer（）

和

sess.run（'init'）

，以确保定义了每个变量。但奇怪的是，错误

Attempting to use uninitialized value Layers/output_layer/weight_out/W_out" still happened in W_out, so as W1_Hidden_1 and W2_Hidden_2...

有人能帮我吗？这是我的代码

with tf.name_scope('Layers'):
# Initializers
weight_initializer = tf.contrib.layers.variance_scaling_initializer(factor=1.0, mode="FAN_AVG", uniform=True)
bias_initializer = tf.zeros_initializer()

with tf.name_scope('Hidden_layer_1'):
    with tf.name_scope('weight_1'):
        W_hidden_1 = tf.Variable(weight_initializer([n_stocks, n_neurons_1]), name = 'W_Hidden_1')
    with tf.name_scope('bias_1'):
        bias_hidden_1 = tf.Variable(bias_initializer([n_neurons_1]), name = 'Bias_Hidden_1')
    with tf.name_scope('hidden_1_output'):
        hidden_1 = tf.nn.relu(tf.add(tf.matmul(X, W_hidden_1), bias_hidden_1))

with tf.name_scope('Hidden_layer_2'):
    with tf.name_scope('weight_2'):
        W_hidden_2 = tf.Variable(weight_initializer([n_neurons_1, n_neurons_2]), name = 'W_Hidden_2')
    with tf.name_scope('bias_2'):
        bias_hidden_2 = tf.Variable(bias_initializer([n_neurons_2]), name = 'Bias_Hidden_2')
    with tf.name_scope('hidden_2_output'):
        hidden_2 = tf.nn.relu(tf.add(tf.matmul(hidden_1, W_hidden_2), bias_hidden_2))

with tf.name_scope('output_layer'):
    with tf.name_scope('weight_out'):
        W_out = tf.Variable(weight_initializer([n_neurons_2, 1]), name = 'W_out')
    with tf.name_scope('bias_out'):
        bias_out = tf.Variable(bias_initializer([1]), name = 'Bias_out')
    with tf.name_scope('output'):
        output = tf.transpose(tf.add(tf.matmul(hidden_2, W_out), bias_out))

with tf.name_scope('loss'):
    # Cost function
    loss = tf.reduce_mean(tf.square(output - Y))
    tf.summary.scalar('loss', loss)

with tf.name_scope('train'):
    # Optimizer
    train_step = tf.train.AdamOptimizer().minimize(loss)

# Init
init = tf.global_variables_initializer()

merged = tf.summary.merge_all()

with tf.Session() as sess:
    sess.run(init)
    writer = tf.summary.FileWriter('logs/', sess.graph)