如何将 L1 正则化准确添加到张量流误差函数中

嘿，我是张量流的新手，即使经过很多努力也无法添加 L1 正则化项到误差项

x = tf.placeholder("float", [None, n_input])
# Weights and biases to hidden layer
ae_Wh1 = tf.Variable(tf.random_uniform((n_input, n_hidden1), -1.0 / math.sqrt(n_input), 1.0 / math.sqrt(n_input)))
ae_bh1 = tf.Variable(tf.zeros([n_hidden1]))
ae_h1 = tf.nn.tanh(tf.matmul(x,ae_Wh1) + ae_bh1)

ae_Wh2 = tf.Variable(tf.random_uniform((n_hidden1, n_hidden2), -1.0 / math.sqrt(n_hidden1), 1.0 / math.sqrt(n_hidden1)))
ae_bh2 = tf.Variable(tf.zeros([n_hidden2]))
ae_h2 = tf.nn.tanh(tf.matmul(ae_h1,ae_Wh2) + ae_bh2)

ae_Wh3 = tf.transpose(ae_Wh2)
ae_bh3 = tf.Variable(tf.zeros([n_hidden1]))
ae_h1_O = tf.nn.tanh(tf.matmul(ae_h2,ae_Wh3) + ae_bh3)

ae_Wh4 = tf.transpose(ae_Wh1)
ae_bh4 = tf.Variable(tf.zeros([n_input]))
ae_y_pred = tf.nn.tanh(tf.matmul(ae_h1_O,ae_Wh4) + ae_bh4)



ae_y_actual = tf.placeholder("float", [None,n_input])
meansq = tf.reduce_mean(tf.square(ae_y_actual - ae_y_pred))
train_step = tf.train.GradientDescentOptimizer(0.05).minimize(meansq)

之后我使用运行上面的图表

init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

n_rounds = 100
batch_size = min(500, n_samp)
for i in range(100):
    sample = np.random.randint(n_samp, size=batch_size)
    batch_xs = input_data[sample][:]
    batch_ys = output_data_ae[sample][:]
    sess.run(train_step, feed_dict={x: batch_xs, ae_y_actual:batch_ys})

Above是4层的代码自动编码器， “meansq”是我的平方损失函数。如何为网络中的权重矩阵（张量）添加 L1 正则化？

您可以使用 TensorFlow应用正则化 https://www.tensorflow.org/api_docs/python/tf/contrib/layers/apply_regularization and l1_正则化器 https://www.tensorflow.org/api_docs/python/tf/contrib/layers/l1_regularizer方法。Note：这是针对 Tensorflow 1 的，API 在 Tensorflow 2 中发生了变化，请参阅下面的编辑。

基于您的问题的示例：

import tensorflow as tf

total_loss = meansq #or other loss calcuation
l1_regularizer = tf.contrib.layers.l1_regularizer(
   scale=0.005, scope=None
)
weights = tf.trainable_variables() # all vars of your graph
regularization_penalty = tf.contrib.layers.apply_regularization(l1_regularizer, weights)

regularized_loss = total_loss + regularization_penalty # this loss needs to be minimized
train_step = tf.train.GradientDescentOptimizer(0.05).minimize(regularized_loss)

Note: weights is a list其中每个条目是一个tf.Variable.

Edited: As Paddy https://stackoverflow.com/users/5324310/paddy正确地指出，在 Tensorflow 2 中，他们更改了正则化器的 API。在Tensorflow 2中，描述了L1正则化here https://www.tensorflow.org/api_docs/python/tf/keras/regularizers/l1.