Unconnected series in Tensorflow graph

Question

My sparse autoencoder model consisted of mainly 10 convolutions and 10 transpose convolution layers. After completion of training, I am getting the graph in the Tensorboard like below.

My understanding says that this graph is not connected because Conv1 and Conv2 are unconnected. This is my first Tensorflow model, so I am confused. Please suggest what is the wrong I am doing. This code has been developed based on CIFAR10 multi GPU code.

Model Snippet

def inference(images, labels, keep_prob, batch_size):
  """Build the cnn model.
  Args:
    images: Images returned from distorted_inputs() or inputs().
    keep_prob: Dropout probability
  Returns:
    Logits.
  """

# conv1
  with tf.variable_scope('conv1') as scope:
    kernel1 = _variable_with_weight_decay('weights', shape=[5, 5, model_params.org_image['channels'], 100], stddev=1e-4, wd=0.0)
    conv1 = tf.nn.conv2d(images, kernel1, [1, 1, 1, 1], padding='SAME')
    biases1 = _variable_on_cpu('biases', [100], tf.constant_initializer(0.0))
    bias1 = tf.nn.bias_add(conv1, biases1)
    conv1 = tf.nn.relu(bias1, name=scope.name)
    print(tf.abs(conv1))
    _activation_summary(conv1)

  # norm1
  norm1 = tf.nn.batch_normalization(conv1, mean=0.6151888371, variance=0.2506813109, offset=None, scale=False, variance_epsilon=0.001, name='norm1') 

  # conv2
  with tf.variable_scope('conv2') as scope:
    kernel2 = _variable_with_weight_decay('weights', shape=[5, 5, 100, 120], stddev=1e-4, wd=0.0)
    conv2 = tf.nn.conv2d(norm1, kernel2, [1, 1, 1, 1], padding='SAME')
    biases2 = _variable_on_cpu('biases', [120], tf.constant_initializer(0.1))
    bias2 = tf.nn.bias_add(conv2, biases2)
    conv2 = tf.nn.relu(bias2, name=scope.name)
    print(tf.abs(conv2))
    _activation_summary(conv2)

  # norm2
  norm2 = tf.nn.batch_normalization(conv2, mean=0.6151888371, variance=0.2506813109, offset=None, scale=False, variance_epsilon=0.001, name='norm2')
  # pool2

....

Even I am not understanding why "IsVariable" is showing in my graph. Any type of help will be highly appreciated.

Update

I found this solution which says that "multi-GPU graph looks like that is because the namescoping in the multi-GPU version creates tower_N namespaces that have incoming edges (tensors) above a certain threshold, at which point we extract those nodes on the side since usually they end up being auxiliary and not part of the main net architecture." Still, I am confused if my graph is perfect or not.

Answer 1

I ran the original CIFAR10 multi GPU code and check the CIFAR10 tensorboard outcome which is similar to my graph. So my conclusion is my graph is fine.