How to correctly use the tf.layers.batch_normalization() in tensorflow?

I'm confused by the tf.layers.batch_normalization in tensorflow.

My code is as follows:

def my_net(x, num_classes, phase_train, scope):
    x = tf.layers.conv2d(...)
    x = tf.layers.batch_normalization(x, training=phase_train)
    x = tf.nn.relu(x) 
    x = tf.layers.max_pooling2d(...)

    # some other staffs
    ...

    # return 
    return x

def train():
    phase_train = tf.placeholder(tf.bool, name='phase_train')
    image_node = tf.placeholder(tf.float32, shape=[batch_size, HEIGHT, WIDTH, 3])
    images, labels = data_loader(train_set)
    val_images, val_labels = data_loader(validation_set)
    prediction_op = my_net(image_node, num_classes=2,phase_train=phase_train, scope='Branch1')

    loss_op = loss(...)
    # some other staffs
    optimizer = tf.train.AdamOptimizer(base_learning_rate)
    update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
    with tf.control_dependencies(update_ops):
        train_op = optimizer.minimize(loss=total_loss, global_step=global_step)
    sess = ...
    coord = ...
    while not coord.should_stop():
        image_batch, label_batch = sess.run([images, labels])
        _,loss_value= sess.run([train_op,loss_op], feed_dict={image_node:image_batch,label_node:label_batch,phase_train:True})

        step = step+1

        if step==NUM_TRAIN_SAMPLES:
            for _ in range(NUM_VAL_SAMPLES/batch_size):
                image_batch, label_batch = sess.run([val_images, val_labels])
                prediction_batch = sess.run([prediction_op], feed_dict={image_node:image_batch,label_node:label_batch,phase_train:False})
            val_accuracy = compute_accuracy(...)


def test():
    phase_train = tf.placeholder(tf.bool, name='phase_train')
    image_node = tf.placeholder(tf.float32, shape=[batch_size, HEIGHT, WIDTH, 3])
    test_images, test_labels = data_loader(test_set)
    prediction_op = my_net(image_node, num_classes=2,phase_train=phase_train, scope='Branch1')

    # some staff to load the trained weights to the graph
    saver.restore(...)

    for _ in range(NUM_TEST_SAMPLES/batch_size):
        image_batch, label_batch = sess.run([test_images, test_labels])
        prediction_batch = sess.run([prediction_op], feed_dict={image_node:image_batch,label_node:label_batch,phase_train:False})
    test_accuracy = compute_accuracy(...)

The training seems to work well and the val_accuracy is reasonable (say 0.70). The problem is: when I tried to use the trained model to do test (i.e., the test function), if the phase_train is set to False, the test_accuracy is very low (say, 0.000270), but when the phase_train is set to True, the test_accuracy seems right (say 0.69).

As far as I understood, the phase_train should be False in testing stage, right? I'm not sure what the problem is. Do I misunderstand the batch normalization?