使用 contrib.learn
库进行此操作的另一种选择是根据 Tensorflow 网站上的Deep MNIST 教程,按照以下方式进行。首先,假设您已经导入了相关库(例如 import tensorflow.contrib.layers as layers
),则可以在单独的方法中定义网络:
def easier_network(x, reg):
""" A network based on tf.contrib.learn, with input `x`. """
with tf.variable_scope('EasyNet'):
out = layers.flatten(x)
out = layers.fully_connected(out,
num_outputs=200,
weights_initializer = layers.xavier_initializer(uniform=True),
weights_regularizer = layers.l2_regularizer(scale=reg),
activation_fn = tf.nn.tanh)
out = layers.fully_connected(out,
num_outputs=200,
weights_initializer = layers.xavier_initializer(uniform=True),
weights_regularizer = layers.l2_regularizer(scale=reg),
activation_fn = tf.nn.tanh)
out = layers.fully_connected(out,
num_outputs=10,
weights_initializer = layers.xavier_initializer(uniform=True),
weights_regularizer = layers.l2_regularizer(scale=reg),
activation_fn = None)
return out
然后,在主方法中,您可以使用以下代码片段:
def main(_):
mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
y_conv = easier_network(x, FLAGS.regu)
weights = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, 'EasyNet')
print("")
for w in weights:
shp = w.get_shape().as_list()
print("- {} shape:{} size:{}".format(w.name, shp, np.prod(shp)))
print("")
reg_ws = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES, 'EasyNet')
for w in reg_ws:
shp = w.get_shape().as_list()
print("- {} shape:{} size:{}".format(w.name, shp, np.prod(shp)))
print("")
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
loss_fn = cross_entropy + tf.reduce_sum(reg_ws)
train_step = tf.train.AdamOptimizer(1e-4).minimize(loss_fn)
要使此功能正常工作,您需要按照我早先提供的MNIST教程并导入相关库,但这是一个很好的练习,可以学习TensorFlow并且很容易看到正则化如何影响输出。如果您将正则化作为参数应用,您可以看到以下内容:
- EasyNet/fully_connected/weights:0 shape:[784, 200] size:156800
- EasyNet/fully_connected/biases:0 shape:[200] size:200
- EasyNet/fully_connected_1/weights:0 shape:[200, 200] size:40000
- EasyNet/fully_connected_1/biases:0 shape:[200] size:200
- EasyNet/fully_connected_2/weights:0 shape:[200, 10] size:2000
- EasyNet/fully_connected_2/biases:0 shape:[10] size:10
- EasyNet/fully_connected/kernel/Regularizer/l2_regularizer:0 shape:[] size:1.0
- EasyNet/fully_connected_1/kernel/Regularizer/l2_regularizer:0 shape:[] size:1.0
- EasyNet/fully_connected_2/kernel/Regularizer/l2_regularizer:0 shape:[] size:1.0
请注意,正则化部分会根据可用项给出三个条目。
当使用正则化参数为0、0.0001、0.01和1.0时,我得到的测试准确率分别为0.9468、0.9476、0.9183和0.1135,这表明高正则化项的危险性。
S = tf.get_variable(name='S', regularizer=tf.contrib.layers.l2_regularizer )
吗? - Charlie Parker