tensorflow - What's meaning of "n tensors" in TensorBoard graph? -

i'm reading tensorflow tutorial code mnist_deep.py , save graph.

the ouput of scope fc1 should have shape [-1, 1024]. it's 2 tensors in graph in tensorboard.

what's meaning of "n tensors" in tensorboard graph?

  # connected layer 1 -- after 2 round of downsampling, our 28x28 image   # down 7x7x64 feature maps -- maps 1024 features.   tf.name_scope('fc1'):     w_fc1 = weight_variable([7 * 7 * 64, 1024])     b_fc1 = bias_variable([1024])      h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])     h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1)    # dropout - controls complexity of model, prevents co-adaptation of   # features.   tf.name_scope('dropout'):     keep_prob = tf.placeholder(tf.float32)     h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) 

it should mean output tensor of relu used twice in droupout node. if try expanding should see input go 2 different nodes.