rewrite training function to include average_grad

[zhangyu2ustc]

def train():
  """Train CIFAR-10 for a number of steps."""
  with tf.Graph().as_default(), tf.device('/cpu:0'):
    # Create a variable to count the number of train() calls. This equals the
    # number of batches processed * FLAGS.num_gpus.
    global_step = tf.get_variable(
        'global_step', [],
        initializer=tf.constant_initializer(0), trainable=False)

    # Calculate the learning rate schedule.
    num_batches_per_epoch = (cifar10.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN /
                             FLAGS.batch_size / FLAGS.num_gpus)
    decay_steps = int(num_batches_per_epoch * cifar10.NUM_EPOCHS_PER_DECAY)

    # Decay the learning rate exponentially based on the number of steps.
    lr = tf.train.exponential_decay(cifar10.INITIAL_LEARNING_RATE,
                                    global_step,
                                    decay_steps,
                                    cifar10.LEARNING_RATE_DECAY_FACTOR,
                                    staircase=True)

    # Create an optimizer that performs gradient descent.
    opt = tf.train.GradientDescentOptimizer(lr)

    # Get images and labels for CIFAR-10.
    images, labels = cifar10.distorted_inputs()
    batch_queue = tf.contrib.slim.prefetch_queue.prefetch_queue(
          [images, labels], capacity=2 * FLAGS.num_gpus)
    # Calculate the gradients for each model tower.
    tower_grads = []
    with tf.variable_scope(tf.get_variable_scope()):
      for i in xrange(FLAGS.num_gpus):
        with tf.device('/gpu:%d' % i):
          with tf.name_scope('%s_%d' % (cifar10.TOWER_NAME, i)) as scope:
            # Dequeues one batch for the GPU
            image_batch, label_batch = batch_queue.dequeue()
            # Calculate the loss for one tower of the CIFAR model. This function
            # constructs the entire CIFAR model but shares the variables across
            # all towers.
            loss = tower_loss(scope, image_batch, label_batch)

            # Reuse variables for the next tower.
            tf.get_variable_scope().reuse_variables()

            # Retain the summaries from the final tower.
            summaries = tf.get_collection(tf.GraphKeys.SUMMARIES, scope)

            # Calculate the gradients for the batch of data on this CIFAR tower.
            grads = opt.compute_gradients(loss)

            # Keep track of the gradients across all towers.
            tower_grads.append(grads)

    # We must calculate the mean of each gradient. Note that this is the
    # synchronization point across all towers.
    grads = average_gradients(tower_grads)

    # Add a summary to track the learning rate.
    summaries.append(tf.summary.scalar('learning_rate', lr))

    # Add histograms for gradients.
    for grad, var in grads:
      if grad is not None:
        summaries.append(tf.summary.histogram(var.op.name + '/gradients', grad))

    # Apply the gradients to adjust the shared variables.
    apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)

[zhangyu2ustc]

Give up on this...