Question

嗨，我是神经网络的新手，我目前正在研究Tensoflow。首先，我做了MNIST教程，效果很好。现在，我想通过Google Colab中自己的Cifar10网络来加深整体。为此，我编写了以下代码：

def conv2d(input, size, inputDim, outputCount):
  with tf.variable_scope("conv2d"): 
    ## -> This area causes problems <- ##
    ##########variant1
    weight = tf.Variable(tf.truncated_normal([size, size, inputDim, outputCount], stddev=0.1),name="weight")
    bias = tf.Variable( tf.constant(0.1, shape=[outputCount]),name="bias")
    ##########variant2
    weight = tf.get_variable("weight", tf.truncated_normal([size, size, inputDim, outputCount], stddev=0.1))
    bias = tf.get_variable("bias", tf.constant(0.1, shape=[outputCount]))
    ##################
    conv = tf.nn.relu(tf.nn.conv2d(input, weight, strides=[1, 1, 1, 1], padding='SAME') + bias)    
  return conv

def maxPool(conv2d):....

def fullyConnect(input, inputSize, outputCount, relu):
  with tf.variable_scope("fullyConnect"):
    ## -> This area causes problems <- ##
    ##########variant1
    weight = tf.Variable( tf.truncated_normal([inputSize, outputCount], stddev=0.1),name="weight")
    bias = tf.Variable( tf.constant(0.1, shape=[outputCount]),name="bias")
    ##########variant2
    weight = tf.get_variable("weight", tf.truncated_normal([inputSize, outputCount], stddev=0.1))
    bias = tf.get_variable("bias", tf.constant(0.1, shape=[outputCount]))
    ##################            
    fullyIn = tf.reshape(input, [-1, inputSize])        
    fullyCon = fullyIn
    if relu:
      fullyCon = tf.nn.relu(tf.matmul(fullyIn, weight) + bias)
  return fullyCon

#Model Def.
def getVGG16A(grafic,width,height,dim):
  with tf.name_scope("VGG16A"):    
    img = tf.reshape(grafic, [-1,width,height,dim])
    with tf.name_scope("Layer1"): 
      with tf.variable_scope("Layer1"):   
        with tf.variable_scope("conv1"):
          l1_c = conv2d(img,3, dim, 64)        
        with tf.variable_scope("mp1"):
          l1_mp = maxPool(l1_c) #32 > 16

    with tf.name_scope("Layer2"):
      with tf.variable_scope("Layer2"):  
        with tf.variable_scope("conv1"):
          l2_c = conv2d(l1_mp,3, 64, 128)
        with tf.variable_scope("mp1"):
          l2_mp = maxPool(l2_c) #16 > 8

    with tf.name_scope("Layer6"):
      with tf.variable_scope("Layer6"):  
        with tf.variable_scope("fully1"):
          L6_fc1 = fullyConnect(l2_mp, 8*8*128 , 1024, True)
        with tf.variable_scope("fully2"):
          L6_fc2 = fullyConnect(L6_fc1, 1024, 1024, True)         

        keep_prob = tf.placeholder(tf.float32)
        drop = tf.nn.dropout(L6_fc2, keep_prob)

        with tf.variable_scope("fully3"):
          L6_fc3 = fullyConnect(drop,1024, 3, False)
  return L6_fc3, keep_prob

x = tf.placeholder(tf.float32, [None, 3072]) #input
y_ = tf.placeholder(tf.float32, [None, 3])   #output

# Build the graph for the deep net
y_conv, keep_prob = getVGG16A(x,32,32,3) #create Model

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-3).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.Session() as sess:
  sess.run(tf.global_variables_initializer())   

  for batch in getBatchData(prep_filter_dataBatch1,2): #a self-written method for custom batch return

    train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.8})

  print('test accuracy %g' % accuracy.eval(feed_dict={
      x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

为了定义张量流变量，我首先使用了variant1（tf.variable）。重复执行后，这会导致图形内存溢出。然后，我使用了variant2（tf.get_variable）。如果我正确理解了文档，则应该使用已经存在的变量（如果存在）。

但是，一旦执行此操作，我会收到以下错误消息：

TypeError: Tensor objects are not iterable when eager execution is not enabled. To iterate over this tensor use tf.map_fn.

我一直在看黑洞日，但是我没有找到解释。

现在我希望这里有人可以向我解释为什么这不可能或在哪里可以找到更多信息。错误消息使我无处可去。我不需要解决方案，因为我想要并且必须了解这一点，因为我想在CNN领域写我的学士论文。

为什么我应该使用tf.variable而不是tf.get_variable，它应该做同样的事情？

感谢您的帮助，最好的问候，帕斯卡尔：）

Answer 1

我发现了我的错误。我忘记了关键字initializer。

正确的行如下所示：

weight = tf.get_variable("weight",initializer=tf.truncated_normal([size, size, inputDim, outputCount], stddev=anpassung))

在Tensorflow中将tf.get_variable用作tf.Variable的替代时出错

1 个答案: