TensorFlow重用变量与tf.layers.conv2d

Question

我试图使2转换层共享相同的权重,但是,似乎API不起作用.

import tensorflow as tf

x = tf.random_normal(shape=[10, 32, 32, 3])

with tf.variable_scope('foo') as scope:
    conv1 = tf.contrib.layers.conv2d(x, 3, [2, 2], padding='SAME', reuse=True, scope=scope)
    print(conv1.name)

    conv2 = tf.contrib.layers.conv2d(x, 3, [2, 2], padding='SAME', reuse=True, scope=scope)
    print(conv2.name)

打印出来

foo/foo/Relu:0
foo/foo_1/Relu:0

从改变tf.contrib.layers.conv2d到tf.layers.conv2d不解决问题.

它有同样的问题tf.layers.conv2d:

import tensorflow as tf

x = tf.random_normal(shape=[10, 32, 32, 3])

conv1 = tf.layers.conv2d(x, 3, [2, 2], padding='SAME', reuse=None, name='conv')
print(conv1.name)
conv2 = tf.layers.conv2d(x, 3, [2, 2], padding='SAME', reuse=True, name='conv')
print(conv2.name)

给

conv/BiasAdd:0
conv_2/BiasAdd:0

Answer 1

在您编写的代码中,变量确实在两个卷积层之间重用.试试这个 :

import tensorflow as tf

x = tf.random_normal(shape=[10, 32, 32, 3])

conv1 = tf.layers.conv2d(x, 3, [2, 2], padding='SAME', reuse=None, name='conv')

conv2 = tf.layers.conv2d(x, 3, [2, 2], padding='SAME', reuse=True, name='conv')

print([x.name for x in tf.global_variables()])

# prints
# [u'conv/kernel:0', u'conv/bias:0']

请注意,只创建了一个权重和一个偏差张量.即使它们共享权重,层也不共享实际计算.因此,您会看到操作的两个不同名称.