TensorFlow变量共享解析

转载自：http://blog.csdn.net/jerr__y/article/details/70809528

• name_scope: 为了更好地管理变量的命名空间而提出的。比如在 tensorboard 中，因为引入了 name_scope，我们的 Graph 看起来才井然有序。
• variable_scope: 大大大部分情况下，跟 tf.get_variable() 配合使用，实现变量共享的功能。
• tf.name_scope() 并不会对 tf.get_variable() 创建的变量有任何影响。
  -
  1、未权值共享代码

import tensorflow as tf
# 设置GPU按需增长
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)

# 拿官方的例子改动一下
def my_image_filter():
    conv1_weights = tf.Variable(tf.random_normal([5, 5, 32, 32]),
        name="conv1_weights")
    conv1_biases = tf.Variable(tf.zeros([32]), name="conv1_biases")
    conv2_weights = tf.Variable(tf.random_normal([5, 5, 32, 32]),
        name="conv2_weights")
    conv2_biases = tf.Variable(tf.zeros([32]), name="conv2_biases")
    return None

# First call creates one set of 4 variables.
result1 = my_image_filter()
# Another set of 4 variables is created in the second call.
result2 = my_image_filter()
# 获取所有的可训练变量
vs = tf.trainable_variables()
print 'There are %d train_able_variables in the Graph: ' % len(vs)
for v in vs:
    print v

There are 8 train_able_variables in the Graph: 
Tensor("conv1_weights/read:0", shape=(5, 5, 32, 32), dtype=float32)
Tensor("conv1_biases/read:0", shape=(32,), dtype=float32)
Tensor("conv2_weights/read:0", shape=(5, 5, 32, 32), dtype=float32)
Tensor("conv2_biases/read:0", shape=(32,), dtype=float32)
Tensor("conv1_weights_1/read:0", shape=(5, 5, 32, 32), dtype=float32)
Tensor("conv1_biases_1/read:0", shape=(32,), dtype=float32)
Tensor("conv2_weights_1/read:0", shape=(5, 5, 32, 32), dtype=float32)
Tensor("conv2_biases_1/read:0", shape=(32,), dtype=float32)

2、权值共享代码

import tensorflow as tf
# 设置GPU按需增长
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)

# 下面是定义一个卷积层的通用方式
def conv_relu(kernel_shape, bias_shape):
    # Create variable named "weights".
    weights = tf.get_variable("weights", kernel_shape, initializer=tf.random_normal_initializer())
    # Create variable named "biases".
    biases = tf.get_variable("biases", bias_shape, initializer=tf.constant_initializer(0.0))
    return None


def my_image_filter():
    # 按照下面的方式定义卷积层，非常直观，而且富有层次感
    with tf.variable_scope("conv1"):
        # Variables created here will be named "conv1/weights", "conv1/biases".
        relu1 = conv_relu([5, 5, 32, 32], [32])
    with tf.variable_scope("conv2"):
        # Variables created here will be named "conv2/weights", "conv2/biases".
        return conv_relu( [5, 5, 32, 32], [32])


with tf.variable_scope("image_filters") as scope:
    # 下面我们两次调用 my_image_filter 函数，但是由于引入了 变量共享机制
    # 可以看到我们只是创建了一遍网络结构。
    result1 = my_image_filter()
    scope.reuse_variables()
    result2 = my_image_filter()


# 看看下面，完美地实现了变量共享！！！
vs = tf.trainable_variables()
print 'There are %d train_able_variables in the Graph: ' % len(vs)
for v in vs:
    print v

There are 4 train_able_variables in the Graph: 
Tensor("image_filters/conv1/weights/read:0", shape=(5, 5, 32, 32), dtype=float32)
Tensor("image_filters/conv1/biases/read:0", shape=(32,), dtype=float32)
Tensor("image_filters/conv2/weights/read:0", shape=(5, 5, 32, 32), dtype=float32)
Tensor("image_filters/conv2/biases/read:0", shape=(32,), dtype=float32)