本文翻譯自: 《Scopes and when to use them》, 若有侵權請聯繫刪除,僅限於學術交流,請勿商用。若有謬誤,請聯繫指出。python
在TensorFlow中,變量(Variables)和張量(tensors)有一個名字(name)屬性,用於在符號圖中標識它們。若是在建立變量或張量時未指定名稱,TensorFlow會自動爲您指定名稱:git
a = tf.constant(1)
print(a.name) # prints "Const:0"
b = tf.Variable(1)
print(b.name) # prints "Variable:0"
複製代碼
您能夠經過顯式指定來覆蓋默認名稱:github
a = tf.constant(1, name="a")
print(a.name) # prints "a:0"
b = tf.Variable(1, name="b")
print(b.name) # prints "b:0"
複製代碼
TensorFlow引入了兩個不一樣的上下文管理器來改變張量和變量的名稱。第一個是tf.name_scope
:bash
with tf.name_scope("scope"):
a = tf.constant(1, name="a")
print(a.name) # prints "scope/a:0"
b = tf.Variable(1, name="b")
print(b.name) # prints "scope/b:0"
c = tf.get_variable(name="c", shape=[])
print(c.name) # prints "c:0"
複製代碼
請注意,有兩種方法能夠在TensorFlow中定義新變量,一是建立tf.Variable
對象或是調用tf.get_variable
方法。使用新名稱調用tf.get_variable
會致使建立新變量,但若是存在具備相同名稱的變量,則會引起ValueError異常,告訴咱們不容許從新聲明變量。網絡
tf.name_scope
影響使用tf.Variable
建立的張量和變量的名稱,但不影響使用tf.get_variable
建立的變量。函數
與tf.name_scope
不一樣,tf.variable_scope
也修改了使用tf.get_variable
建立的變量的名稱:ui
with tf.variable_scope("scope"):
a = tf.constant(1, name="a")
print(a.name) # prints "scope/a:0"
b = tf.Variable(1, name="b")
print(b.name) # prints "scope/b:0"
c = tf.get_variable(name="c", shape=[])
print(c.name) # prints "scope/c:0"
with tf.variable_scope("scope"):
a1 = tf.get_variable(name="a", shape=[])
a2 = tf.get_variable(name="a", shape=[]) # Disallowed
複製代碼
可是,若是咱們真的想要複用先前聲明的變量呢?變量範圍還提供了執行此操做的功能:spa
with tf.variable_scope("scope"):
a1 = tf.get_variable(name="a", shape=[])
with tf.variable_scope("scope", reuse=True):
a2 = tf.get_variable(name="a", shape=[]) # OK
複製代碼
這在使用內置神經網絡層時變得很方便:翻譯
with tf.variable_scope('my_scope'):
features1 = tf.layers.conv2d(image1, filters=32, kernel_size=3)
# Use the same convolution weights to process the second image:
with tf.variable_scope('my_scope', reuse=True):
features2 = tf.layers.conv2d(image2, filters=32, kernel_size=3)
複製代碼
或者,您能夠將reuse
屬性設置爲tf.AUTO_REUSE
,這種操做告訴TensorFlow若是不存在具備相同名稱的變量,就建立新變量,不然就複用:code
with tf.variable_scope("scope", reuse=tf.AUTO_REUSE):
features1 = tf.layers.conv2d(image1, filters=32, kernel_size=3)
with tf.variable_scope("scope", reuse=tf.AUTO_REUSE):
features2 = tf.layers.conv2d(image2, filters=32, kernel_size=3)
複製代碼
若是你想共享不少變量,跟蹤定義新變量以及複用這些變量的時候可能很麻煩且容易出錯。tf.AUTO_REUSE
則簡化了此任務,但增長了共享不該共享的變量的風險。TensorFlow模板是解決這一問題的另外一種方法,它沒有這種風險:
conv3x32 = tf.make_template("conv3x32", lambda x: tf.layers.conv2d(x, 32, 3))
features1 = conv3x32(image1)
features2 = conv3x32(image2) # Will reuse the convolution weights.
複製代碼
您能夠將任何功能轉換爲TensorFlow模板。在第一次調用模板時,在函數內部定義的變量會被聲明,而且在連續調用中,它們將被自動複用。