tensorflow - 如何在tensorflow中正确使用tf.layers.batch_normalization()？

Question

我对 tensorflow 中的 tf.layers.batch_normalization 感到困惑。

我的代码如下:

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(...)

训练似乎效果很好，并且 val_accuracy 是合理的(比如 0.70)。问题是:当我尝试使用训练好的模型进行测试(即 test 函数)时，如果 phase_train 设置为 False，test_accuracy 非常低(例如 0.000270)，但是当 phase_train 设置为 True 时， test_accuracy 似乎是正确的(例如 0.69)。

据我了解，在测试阶段phase_train应该是False，对吗？我不确定问题是什么。我是否误解了批量归一化？

Answer 1

这可能是您的代码中的一些错误，或者只是过度拟合。如果您对训练数据进行评估，准确性是否与训练期间一样高？如果问题出在批量归一化上，那么在没有训练的情况下，训练误差会比在训练模式下更高。如果问题是过度拟合，那么批量归一化可能不会导致该问题，根本原因在其他地方。