Tensorflow函数说明(4)—— variable_scope/name_scope
2017-04-07 08:18
483 查看
主要针对 tf.get_variable 来介绍共享变量的用法。
tf.get_variable 与 tf.variable 的用法不同。前者在创建变量时会查名字,如果给的名字在之前已经被别的变量占用,则会报错,不会创建相应变量。而后者并不进行检查,如果有重复,则自动的修改名字,加上数字来进行区别。所以从这来看要想共享变量并不能通过使用相同的名字来调用多次 tf.get_variable
和 tf.variable 做到。
比如下面这样的代码:
def my_image_filter(input_images):
conv1_weights = tf.Variable(tf.random_normal([5, 5, 32, 32]),
name="conv1_weights")
conv1_biases = tf.Variable(tf.zeros([32]), name="conv1_biases")
conv1 = tf.nn.conv2d(input_images, conv1_weights,
strides=[1, 1, 1, 1], padding='SAME')
relu1 = tf.nn.relu(conv1 + 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")
conv2 = tf.nn.conv2d(relu1, conv2_weights,
strides=[1, 1, 1, 1], padding='SAME')
return tf.nn.relu(conv2 + conv2_biases)在这个函数中,我们有 'conv1_weights','conv1_biases','conv2_weights','conv2_biases'
4个变量。如果我们重用这个函数,则会产生多组变量,并不会使用相同的变量,如下面调用:
# First call creates one set of variables.
result1 = my_image_filter(image1)
# Another set is created in the second call.
result2 = my_image_filter(image2)上面实际上用两个不同的滤波器对 image1 和 image2 进行滤波,虽然用的是相同的函数。所以呢,这就产生了问题,下面介绍如何进行变量共享。
我们使用 with tf.variable_scope 来进行共享。比如有下面的代码:
def conv_relu(input, 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_intializer(0.0))
conv = tf.nn.conv2d(input, weights,
strides=[1, 1, 1, 1], padding='SAME')
return tf.nn.relu(conv + biases)
def my_image_filter(input_images):
with tf.variable_scope("conv1"):
# Variables created here will be named "conv1/weights", "conv1/biases".
relu1 = conv_relu(input_images, [5, 5, 32, 32], [32])
with tf.variable_scope("conv2"):
# Variables created here will be named "conv2/weights", "conv2/biases".
return conv_relu(relu1, [5, 5, 32, 32], [32])若要调用两次 my_image_filter 并且使用相同的变量,则如下所示:
with tf.variable_scope("image_filters") as scope:
result1 = my_image_filter(image1)
scope.reuse_variables()
result2 = my_image_filter(image2)利用 reuse_variables() 来使变量重用。值得注意的是下面的代码解释了
tf.get_variable 工作原理:
with tf.variable_scope("foo"):
v = tf.get_variable("v", [1])
with tf.variable_scope("foo", reuse=True):
v1 = tf.get_variable("v", [1])
assert v1 == v如果 reuse 开启,当检查到有相同的名字时,直接返回那个有相同名字的变量而不是重新定义一个再复制值。
下面是使用时需要注意的地方
1. 在 variable_scope 里面的 variable_scope 会继承上面的 reuse 值,即上面一层开启了 reuse ,则下面的也跟着开启。但是不能人为的设置 reuse 为 false ,只有退出 variable_scope 才能让 reuse 变为 false:
with tf.variable_scope("root"):
# At start, the scope is not reusing.
assert tf.get_variable_scope().reuse == False
with tf.variable_scope("foo"):
# Opened a sub-scope, still not reusing.
assert tf.get_variable_scope().reuse == False
with tf.variable_scope("foo", reuse=True):
# Explicitly opened a reusing scope.
assert tf.get_variable_scope().reuse == True
with tf.variable_scope("bar"):
# Now sub-scope inherits the reuse flag.
assert tf.get_variable_scope().reuse == True
# Exited the reusing scope, back to a non-reusing one.
assert tf.get_variable_scope().reuse == False
2. 当在某一 variable_scope 内使用别的 scope 的名字时,此时不再受这里的等级关系束缚,直接与使用的 scope 的名字一样:
with tf.variable_scope("foo") as foo_scope:
assert foo_scope.name == "foo"
with tf.variable_scope("bar")
with tf.variable_scope("baz") as other_scope:
assert other_scope.name == "bar/baz"
with tf.variable_scope(foo_scope) as foo_scope2:
assert foo_scope2.name == "foo" # Not changed.
3. name_scope 与 variable_scope 稍有不同。name_scope 只会影响 ops 的名字,而并不会影响 variables 的名字。
with tf.variable_scope("foo"):
with tf.name_scope("bar"):
v = tf.get_variable("v", [1])
x = 1.0 + v
assert v.name == "foo/v:0"
assert x.op.name == "foo/bar/add"
tf.get_variable 与 tf.variable 的用法不同。前者在创建变量时会查名字,如果给的名字在之前已经被别的变量占用,则会报错,不会创建相应变量。而后者并不进行检查,如果有重复,则自动的修改名字,加上数字来进行区别。所以从这来看要想共享变量并不能通过使用相同的名字来调用多次 tf.get_variable
和 tf.variable 做到。
比如下面这样的代码:
def my_image_filter(input_images):
conv1_weights = tf.Variable(tf.random_normal([5, 5, 32, 32]),
name="conv1_weights")
conv1_biases = tf.Variable(tf.zeros([32]), name="conv1_biases")
conv1 = tf.nn.conv2d(input_images, conv1_weights,
strides=[1, 1, 1, 1], padding='SAME')
relu1 = tf.nn.relu(conv1 + 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")
conv2 = tf.nn.conv2d(relu1, conv2_weights,
strides=[1, 1, 1, 1], padding='SAME')
return tf.nn.relu(conv2 + conv2_biases)在这个函数中,我们有 'conv1_weights','conv1_biases','conv2_weights','conv2_biases'
4个变量。如果我们重用这个函数,则会产生多组变量,并不会使用相同的变量,如下面调用:
# First call creates one set of variables.
result1 = my_image_filter(image1)
# Another set is created in the second call.
result2 = my_image_filter(image2)上面实际上用两个不同的滤波器对 image1 和 image2 进行滤波,虽然用的是相同的函数。所以呢,这就产生了问题,下面介绍如何进行变量共享。
我们使用 with tf.variable_scope 来进行共享。比如有下面的代码:
def conv_relu(input, 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_intializer(0.0))
conv = tf.nn.conv2d(input, weights,
strides=[1, 1, 1, 1], padding='SAME')
return tf.nn.relu(conv + biases)
def my_image_filter(input_images):
with tf.variable_scope("conv1"):
# Variables created here will be named "conv1/weights", "conv1/biases".
relu1 = conv_relu(input_images, [5, 5, 32, 32], [32])
with tf.variable_scope("conv2"):
# Variables created here will be named "conv2/weights", "conv2/biases".
return conv_relu(relu1, [5, 5, 32, 32], [32])若要调用两次 my_image_filter 并且使用相同的变量,则如下所示:
with tf.variable_scope("image_filters") as scope:
result1 = my_image_filter(image1)
scope.reuse_variables()
result2 = my_image_filter(image2)利用 reuse_variables() 来使变量重用。值得注意的是下面的代码解释了
tf.get_variable 工作原理:
with tf.variable_scope("foo"):
v = tf.get_variable("v", [1])
with tf.variable_scope("foo", reuse=True):
v1 = tf.get_variable("v", [1])
assert v1 == v如果 reuse 开启,当检查到有相同的名字时,直接返回那个有相同名字的变量而不是重新定义一个再复制值。
下面是使用时需要注意的地方
1. 在 variable_scope 里面的 variable_scope 会继承上面的 reuse 值,即上面一层开启了 reuse ,则下面的也跟着开启。但是不能人为的设置 reuse 为 false ,只有退出 variable_scope 才能让 reuse 变为 false:
with tf.variable_scope("root"):
# At start, the scope is not reusing.
assert tf.get_variable_scope().reuse == False
with tf.variable_scope("foo"):
# Opened a sub-scope, still not reusing.
assert tf.get_variable_scope().reuse == False
with tf.variable_scope("foo", reuse=True):
# Explicitly opened a reusing scope.
assert tf.get_variable_scope().reuse == True
with tf.variable_scope("bar"):
# Now sub-scope inherits the reuse flag.
assert tf.get_variable_scope().reuse == True
# Exited the reusing scope, back to a non-reusing one.
assert tf.get_variable_scope().reuse == False
2. 当在某一 variable_scope 内使用别的 scope 的名字时,此时不再受这里的等级关系束缚,直接与使用的 scope 的名字一样:
with tf.variable_scope("foo") as foo_scope:
assert foo_scope.name == "foo"
with tf.variable_scope("bar")
with tf.variable_scope("baz") as other_scope:
assert other_scope.name == "bar/baz"
with tf.variable_scope(foo_scope) as foo_scope2:
assert foo_scope2.name == "foo" # Not changed.
3. name_scope 与 variable_scope 稍有不同。name_scope 只会影响 ops 的名字,而并不会影响 variables 的名字。
with tf.variable_scope("foo"):
with tf.name_scope("bar"):
v = tf.get_variable("v", [1])
x = 1.0 + v
assert v.name == "foo/v:0"
assert x.op.name == "foo/bar/add"
相关文章推荐
- tensorflow:上下文管理器 与 name_scope, variable_scope
- TensorFlow中,variable_scope和name_scope的不同之处
- tf 共享变量 tensorflow 里面 name_scope, variable_scope
- tensorflow之变量作用域与变量共享(name_scope,variable_scope,get_variable,Variable)
- TensorFlow:作用域name_scope和variable_scope
- TensorFlow基础name_scope与variable_scope
- TensorFlow学习笔记(1):variable与get_variable, name_scope()和variable_scope()
- tensorflow name_scope && variable_scope
- tensorflow 中 name_scope 及 variable_scope 的异同
- tensorflow: name_scope 和 variable_scope的差别
- 2. tensorflow学习之name/variable_scope 的使用
- tensorflow name_scope variable_scope
- tensorflow 中 name_scope 及 variable_scope 的异同
- Tensorflow函数——tf.variable_scope()
- tensorflow 中的 name_scope 与 variable_scope
- 【Tensorflow】name_scope() 和 variable_scope() 区别
- tensorflow 中 name_scope和variable_scope
- TensorFlow 学习(一)—— tf.get_variable() vs tf.Variable(),tf.name_scope() vs tf.variable_scope()
- 关于tensorflow的变量(variable) 变量作用域(variable_scope) 名字作用域(name_scope)的学习记录
- TensorFlow 学习(一)—— tf.get_variable() vs tf.Variable(),tf.name_scope() vs tf.variable_scope()