5

我正在查看 Tensorflow 的力学部分,特别是关于共享变量的部分。在“问题”部分,他们正在处理卷积神经网络,并提供以下代码(通过模型运行图像):

# 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)

如果模型以这种方式实现,那么是否不可能学习/更新参数,因为我的训练集中的每个图像都有一组新的参数?

编辑:我还在一个简单的线性回归示例中尝试了“问题”方法,并且这种实现方法似乎没有任何问题。训练似乎很有效,代码的最后一行也可以看出这一点。所以我想知道 tensorflow 文档和我在做什么之间是否存在细微的差异。:

import tensorflow as tf
import numpy as np

trX = np.linspace(-1, 1, 101)
trY = 2 * trX + np.random.randn(*trX.shape) * 0.33 # create a y value which is         approximately linear but with some random noise

X = tf.placeholder("float") # create symbolic variables
Y = tf.placeholder("float")


def model(X):
    with tf.variable_scope("param"):
        w = tf.Variable(0.0, name="weights") # create a shared variable (like theano.shared) for the weight matrix

    return tf.mul(X, w) # lr is just X*w so this model line is pretty simple


y_model = model(X)

cost = (tf.pow(Y-y_model, 2)) # use sqr error for cost function

train_op = tf.train.GradientDescentOptimizer(0.01).minimize(cost) # construct an optimizer to minimize cost and fit line to my data

sess = tf.Session()
init = tf.initialize_all_variables() # you need to initialize variables (in this case just variable W)
sess.run(init)

with tf.variable_scope("train"):
    for i in range(100):
        for (x, y) in zip(trX, trY):
        sess.run(train_op, feed_dict={X: x, Y: y})

print sess.run(y_model, feed_dict={X: np.array([1,2,3])})
4

1 回答 1

10

每个整个训练(和测试)集只需创建一次变量集。可变范围的目标是允许参数子集的模块化,例如属于层的参数子集(例如,当重复层的架构时,可以在每个层范围内使用相同的名称)。

在您的示例中,您仅在model函数中创建参数。您可以打印出变量名称以查看它是否已分配给指定范围:

from __future__ import print_function

X = tf.placeholder("float") # create symbolic variables
Y = tf.placeholder("float")
print("X:", X.name)
print("Y:", Y.name)

def model(X):
    with tf.variable_scope("param"):
        w = tf.Variable(0.0, name="weights") # create a shared variable (like theano.shared) for the weight matrix
    print("w:", w.name)
    return tf.mul(X, w) 

对 的调用sess.run(train_op, feed_dict={X: x, Y: y})仅评估train_op给定的X和的值Y。那里没有创建新变量(包括参数);因此,它没有效果。您可以通过再次打印它们来确保变量名称保持不变:

with tf.variable_scope("train"):
    print("X:", X.name)
    print("Y:", Y.name)
    for i in range(100):
        for (x, y) in zip(trX, trY):
            sess.run(train_op, feed_dict={X: x, Y: y})

您将看到变量名称保持不变,因为它们已经初始化。

如果您想使用其范围检索变量get_variable,则需要在tf.variable_scope外壳中使用:

with tf.variable_scope("param"):
    w = tf.get_variable("weights", [1])
print("w:", w.name)
于 2015-12-31T13:39:25.910 回答