Tensorflow概要指标未初始化（用于Tensorboard）

Question

我正在尝试使用tensor-board和下面的代码来记录精度和召回的tensorflow汇总统计信息。

我已经添加了全局和局部变量初始值设定项，但是这仍然会引发一个错误，告诉我我有一个未初始化的'recall'值。

有没有人有任何想法，为什么这仍然抛出一个错误？

错误消息是码块

def classifier_graph(x, y, learning_rate=0.1): 

     with tf.name_scope('classifier'): 
       with tf.name_scope('model'): 
         W = tf.Variable(tf.zeros([xdim, ydim]), name='W') 
         b = tf.Variable(tf.zeros([ydim]), name='b') 
         y_ = tf.matmul(x, W) + b 

       with tf.name_scope('cross_entropy'): 
         diff = tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=y_) 
         cross_entropy = tf.reduce_mean(diff) 
         summary = tf.summary.scalar('cross_entropy', cross_entropy) 

       with tf.name_scope('train'): 
         #cross_entropy = tf.reduce_mean(-tf.reduce_sum(y * tf.log(y_), reduction_indices=[1]), name='cross_entropy') 
         train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(cross_entropy) 
         # minimise cross_entropy via GD 

       #with tf.name_scope('init'): 
         #init = tf.global_variables_initializer() 
         #local_init = tf.local_variables_initializer() 
         #init = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer()) 

       with tf.name_scope('init'): 
         init = tf.global_variables_initializer() 
         init_l = tf.local_variables_initializer() 


       with tf.name_scope('metrics'): 
         recall = tf.metrics.recall(y, y_) 
         precision = tf.metrics.precision(y, y_) 

         v_rec = tf.summary.scalar('recall', recall) 
         v_prec = tf.summary.scalar('precision', precision) 

         metrics = tf.summary.merge_all() 

     return [W, b, y_, cross_entropy, train_step, init, init_l, metrics] 



def train_classifier(insamples, outsamples, batch_size, iterations, feature_set_index=1, model=None, device): 
    x = tf.placeholder(tf.float32, [None, xdim], name='x') # None indications arbitrary first dimension 
    y = tf.placeholder(tf.float32, [None, ydim], name='y') 
    W, b, y_, cross_entropy, train_step, init, init_l, metrics = classifier_graph(x, y) 

    with tf.Session(config=config) as sess, tf.device(device): 
     sess.run(init) 
     sess.run(init_l) 
     file_writer = tf.summary.FileWriter(logdir, tf.get_default_graph()) 

     t = 0 
     while t < iterations: 

      t += 1 
      _, err, metrics_str = sess.run([train_step, cross_entropy, metrics], feed_dict={x: batch_x, y: batch_y }) 

      all_err.append(err) 
      file_writer.add_summary(metrics_str,t) 

    return 'Done' 

确切的错误信息以下的是：

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value recall/true_positives/count 
    [[Node: recall/true_positives/count/read = Identity[T=DT_FLOAT, _class=["loc:@recall/true_positives/count"], _device="/job:localhost/replica:0/task:0/gpu:0"](recall/true_positives/count)]] 

谢谢！

编辑：

在作出由下面@Ishant Mrinal建议的修改，我遇到我先前被击中一个错误：

InvalidArgumentError (see above for traceback): tags and values not the same shape: [] != [2] (tag 'precision_1') 

这表明精度张量是不同的形状对其他人来说，它不会为交叉熵或回忆而抛出这个错误。

Answer 1

由于两条初始化线的放置，将这两条线移动到train_classifier函数。错误表明一些变量未被初始化。

def train_classifier(...): 
    ... 
    init = tf.global_variables_initializer() 
    init_l = tf.local_variables_initializer() 
    with tf.Session(config=config) as sess, tf.device(device): 
     sess.run(init) 
     sess.run(init_l) 

Answer 2

的第二个问题是由以下事实：tf.metrics返回两个张量引起的。相反，做

    _, recall = tf.metrics.recall(y, y_) 
        _, precision = tf.metrics.precision(y, y_) 

        v_rec = tf.summary.scalar('recall', recall) 
        v_prec = tf.summary.scalar('precision', precision)