Question

正如标题所述，如何在Tensorflow中初始化variable_scope中的变量？我不知道这是必要的，因为我认为这是一个常数。但是，当我在Android上运行会话时尝试预测输出时，我收到错误：

Error during inference: Failed precondition: Attempting to use uninitialized value weights0

[[Node: weights0/read = Identity[T=DT_FLOAT, _class=["loc:@weights0"], _device="/job:localhost/replica:0/task:0/cpu:0"](weights0)]]

我尝试使用tf.Variable（即'h1': tf.Variable(vs.get_variable("weights0", [n_input, n_hidden_1], initializer=tf.contrib.layers.xavier_initializer()))）设置变量，但我得到错误`tensor name＆＃39; Variable＆＃39;尝试生成protobuf文件时在检查点文件中找不到。

段

def reg_perceptron(t, weights, biases):
    t = tf.nn.relu(tf.add(tf.matmul(t, weights['h1']), biases['b1']), name = "layer_1")
    t = tf.nn.sigmoid(tf.add(tf.matmul(t, weights['h2']), biases['b2']), name = "layer_2")
    t = tf.add(tf.matmul(t, weights['hOut'], name="LOut_MatMul"), biases['bOut'], name="LOut_Add")

    return tf.reshape(t, [-1], name="Y_GroundTruth")

g = tf.Graph()
with g.as_default():
   ...
   rg_weights = {
    'h1': vs.get_variable("weights0", [n_input, n_hidden_1], initializer=tf.contrib.layers.xavier_initializer()),
    'h2': vs.get_variable("weights1", [n_hidden_1, n_hidden_2], initializer=tf.contrib.layers.xavier_initializer()),
    'hOut': vs.get_variable("weightsOut", [n_hidden_2, 1], initializer=tf.contrib.layers.xavier_initializer())
    }


    rg_biases = {
    'b1': vs.get_variable("bias0", [n_hidden_1], initializer=init_ops.constant_initializer(bias_start)),
    'b2': vs.get_variable("bias1", [n_hidden_2], initializer=init_ops.constant_initializer(bias_start)),
    'bOut': vs.get_variable("biasOut", [1], initializer=init_ops.constant_initializer(bias_start))
    }

    pred = reg_perceptron(_x, rg_weights, rg_biases)
    ...
...

g_2 = tf.Graph()
with g_2.as_default():
    ...
    rg_weights_2 = {
    'h1': vs.get_variable("weights0", [n_input, n_hidden_1], initializer=tf.contrib.layers.xavier_initializer()),
    'h2': vs.get_variable("weights1", [n_hidden_1, n_hidden_2], initializer=tf.contrib.layers.xavier_initializer()),
    'hOut': vs.get_variable("weightsOut", [n_hidden_2, 1], initializer=tf.contrib.layers.xavier_initializer())
    }

    rg_biases_2 = {
    'b1': vs.get_variable("bias0", [n_hidden_1], initializer=init_ops.constant_initializer(bias_start)),
    'b2': vs.get_variable("bias1", [n_hidden_2], initializer=init_ops.constant_initializer(bias_start)),
    'bOut': vs.get_variable("biasOut", [1], initializer=init_ops.constant_initializer(bias_start))
    }

    pred_2 = reg_perceptron(_x_2, rg_weights_2, rg_biases_2)
    ...

修改

我可以用错误的方式创建protobuf文件吗？我用于.PB生成的代码可以找到here返回

（此处蓝线代表目标值，而绿线代表预测值。）

而我应该得到

代替（来自http://pastebin.com/RUFa9NkN），尽管两个代码都使用相同的输入和模型。

Answer 1

如果您想使用variable_scope，请尝试以下内容：

def initialize_variable(vs_name, ...): # other necessary arguments
    # a function for initialize variables    
    with tf.variable_scope(vs_name, reuse=None) as vs:
        h1 = tf.get_variable("weights0", [n_input, n_hidden_1], initializer=tf.contrib.layers.xavier_initializer())
        h2 = tf.get_variable("weights1", [n_hidden_1, n_hidden_2], initializer=tf.contrib.layers.xavier_initializer())
        hout = tf.get_variable("weightsOut", [n_hidden_2, 1], initializer=tf.contrib.layers.xavier_initializer())
        b1 = tf.get_variable("bias0", [n_hidden_1], initializer=init_ops.constant_initializer(bias_start))
        b2 = tf.get_variable("bias1", [n_hidden_2], initializer=init_ops.constant_initializer(bias_start))
        bout = tf.get_variable("biasOut", [1], initializer=init_ops.constant_initializer(bias_start))
        vs.reuse_variables()

然后在图中，初始化变量首先使用上面的函数，然后提取变量。

g = tf.Graph()
with g.as_default():
  initialize_variable(vs_name, ...) #fill in other necessary arguments
  with tf.variable_scope(vs_name, reuse=True):
      rg_weights = {'h1' : tf.get_variable("weights0"),
                    'h2' : tf.get_variable("weights1"),
                    'hout' : tf.get_variable("weightsOut")}
      rg_biases = {'b1' : tf.get_variable("bias0"),
                   'b2' : tf.get_variable("bias1"),
                   'bOut': tf.get_variable("biasOut")}
  pred = reg_perceptron(_x, rg_weights, rg_biases)

如果您不想涉及variable_scope，请尝试以下内容......虽然以下内容需要提供初始张量并且不接受初始化器。

g = tf.Graph()
with g.as_default():
   ...
   rg_weights = {'h1': tf.Variable(tf.truncated_normal([n_input, n_hidden1], mean, stddev), name='weights0')
                 'h2': tf.Variable(tf.truncated_normal([n_hidden_1, n_hidden_2],mean, stddev), name="weights1"),
                 'hOut': tf.Variable(tf.truncated_normal([n_hidden_2, 1],mean, stddev), name="weightsOut")}
   ...

以下是关于TensorFlow中的变量共享的documentation and example

如何从variable_scope初始化变量？

1 个答案: