python-3.x - 恢复后的 tensorflow 批量标准化

Question

假设我们创建了一个小型网络:

tf.reset_default_graph()
layers      = [5, 3, 1]
activations = [tf.tanh, tf.tanh,  None]

inp = tf.placeholder(dtype=tf.float32, shape=(None, 2 ), name='inp')
out = tf.placeholder(dtype=tf.float32, shape=(None, 1 ), name='out')

isTraining = tf.placeholder(dtype=tf.bool, shape=(), name='isTraining')

N = inp * 1 # I am lazy
for i, (l, a) in enumerate(zip(layers, activations)):
    N = tf.layers.dense(N, l, None)
    #N = tf.layers.batch_normalization( N,  training = isTraining) # comment this line
    if a is not None:
        N = a(N)

err = tf.reduce_mean((N - out)**2)
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
    opt = tf.train.AdamOptimizer(0.05).minimize(err)

# insert vectors from the batch normalization
tVars = tf.trainable_variables()
graph = tf.get_default_graph()
for v in graph.get_collection(tf.GraphKeys.GLOBAL_VARIABLES): 
    if all([
            ('batch_normalization' in v.name),
            ('optimizer' not in v.name), 
            v not in tVars ]):
        tVars.append(v)

init = tf.global_variables_initializer()
saver = tf.train.Saver(var_list= tVars)

这是为优化而生成的简单 NN。我目前唯一感兴趣的是批量优化(已被注释掉的行)。现在，我们训练这个网络，保存它，恢复它并再次计算误差，我们做的很好:

# Generate random data
N = 1000
X = np.random.rand(N, 2)
y = 2*X[:, 0] + 3*X[:, 1] + 3 
y = y.reshape(-1, 1)

# Run the session and save it
with tf.Session() as sess:
    sess.run(init)
    print('During Training')
    for i in range(3000):
        _, errVal = sess.run([opt, err], feed_dict={inp:X, out:y, isTraining:True})
        if i %500 == 0:
            print(errVal)

    shutil.rmtree('models1', ignore_errors=True)
    os.makedirs('models1')
    path = saver.save( sess, 'models1/model.ckpt' )

# restore the session
print('During testing')
with tf.Session() as sess:
    saver.restore(sess, path)
    errVal = sess.run(err, feed_dict={inp:X, out:y, isTraining:False})
    print( errVal )

这是输出:

During Training
24.4422
0.00330666
0.000314223
0.000106421
6.00441e-05
4.95262e-05
During testing
INFO:tensorflow:Restoring parameters from models1/model.ckpt
5.5899e-05 

另一方面，当我们取消批归一化行的注释时，重新进行上述计算:

During Training
31.7372
1.92066e-05
3.87879e-06
2.55274e-06
1.25418e-06
1.43078e-06
During testing
INFO:tensorflow:Restoring parameters from models1/model.ckpt
0.041519

如您所见，恢复的值与模型预测的相差甚远。有什么我做错了吗？

注意:我知道对于批量标准化，我需要生成小批量。我已经跳过了所有这些以保持代码简单而完整。

Answer 1

批量归一化层，如 Tensorflow 中所定义，需要访问占位符 isTraining (https://www.tensorflow.org/api_docs/python/tf/layers/batch_normalization)。确保在定义层时包含它:tf.layers.batch_normalization(..., training=isTraining, ...) .

原因是批量归一化层有 2 个可训练参数(beta 和 gamma)，这些参数与网络的其余部分一起正常训练，但它们还有 2 个额外参数(批量均值和方差)需要您告诉他们训练.您只需应用上面的配方即可做到这一点。

现在您的代码似乎不是训练均值和方差。相反，它们是随机固定的，并且网络会根据这些进行优化。稍后，当您保存和恢复时，它们会使用不同的值重新初始化，因此网络不会像以前那样运行。