python之tensorflow 执行时间

我在 Python 脚本中有一个函数，我多次调用 ( https://github.com/sankhaMukherjee/NNoptExpt/blob/dev/src/lib/NNlib/NNmodel.py ):我已经为这个例子显着简化了函数。

def errorValW(self, X, y, weights): 
 
    errVal = None 
 
    with tf.Session() as sess: 
        sess.run(tf.global_variables_initializer()) 
 
        nW = len(self.allW) 
        W = weights[:nW]  
        B = weights[nW:] 
 
        for i in range(len(W)): 
            sess.run(tf.assign( self.allW[i], W[i] )) 
 
        for i in range(len(B)): 
            sess.run(tf.assign( self.allB[i], B[i] )) 
 
        errVal = sess.run(self.err,  
            feed_dict = {self.Inp: X, self.Op: y}) 
 
    return errVal 

我多次从另一个函数调用这个函数。当我看到程序日志时，似乎这个功能花费的时间越来越长。显示部分日志:

21:37:12,634 - ... .errorValW ... - Finished the function [errorValW] in 1.477610e+00 seconds 
21:37:14,116 - ... .errorValW ... - Finished the function [errorValW] in 1.481470e+00 seconds 
21:37:15,608 - ... .errorValW ... - Finished the function [errorValW] in 1.490914e+00 seconds 
21:37:17,113 - ... .errorValW ... - Finished the function [errorValW] in 1.504651e+00 seconds 
21:37:18,557 - ... .errorValW ... - Finished the function [errorValW] in 1.443876e+00 seconds 
21:37:20,183 - ... .errorValW ... - Finished the function [errorValW] in 1.625608e+00 seconds 
21:37:21,719 - ... .errorValW ... - Finished the function [errorValW] in 1.534915e+00 seconds 
... many lines later   
22:59:26,524 - ... .errorValW ... - Finished the function [errorValW] in 9.576592e+00 seconds 
22:59:35,991 - ... .errorValW ... - Finished the function [errorValW] in 9.466405e+00 seconds 
22:59:45,708 - ... .errorValW ... - Finished the function [errorValW] in 9.716456e+00 seconds 
22:59:54,991 - ... .errorValW ... - Finished the function [errorValW] in 9.282923e+00 seconds 
23:00:04,407 - ... .errorValW ... - Finished the function [errorValW] in 9.415035e+00 seconds 

有没有人遇到过这样的事情？这让我完全莫名其妙......

编辑:此供引用...

作为引用，该类的初始化程序如下所示。我怀疑 result 变量的图表的大小在逐渐增加。当我尝试使用 tf.train.Saver(tf.trainable_variables()) 保存模型并且该文件的大小不断增加时，我看到了这个问题。我不确定我是否在以任何方式定义模型时犯了错误......

def __init__(self, inpSize, opSize, layers, activations): 
 
    self.inpSize = inpSize 
    self.Inp     = tf.placeholder(dtype=tf.float32, shape=inpSize, name='Inp') 
    self.Op      = tf.placeholder(dtype=tf.float32, shape=opSize, name='Op') 
 
    self.allW    = [] 
    self.allB    = [] 
 
    self.result  = None 
 
    prevSize = inpSize[0] 
    for i, l in enumerate(layers): 
        tempW = tf.Variable( 0.1*(np.random.rand(l, prevSize) - 0.5), dtype=tf.float32, name='W_{}'.format(i) ) 
        tempB = tf.Variable( 0, dtype=tf.float32, name='B_{}'.format(i) ) 
 
        self.allW.append( tempW ) 
        self.allB.append( tempB ) 
 
        if i == 0: 
            self.result = tf.matmul( tempW, self.Inp ) + tempB 
        else: 
            self.result = tf.matmul( tempW, self.result ) + tempB 
 
        prevSize = l 
 
        if activations[i] is not None: 
            self.result = activations[i]( self.result ) 
 
    self.err = tf.sqrt(tf.reduce_mean((self.Op - self.result)**2)) 
 
 
    return 

请您参考如下方法:

您正在 session 上下文中调用 tf.assign。这将在您每次执行 errorValW 函数时不断向您的图表添加操作，随着您的图表变大，执行速度会减慢。根据经验，您应该避免在对数据执行模型时调用 Tensorflow ops(因为这通常在循环内，导致图形不断增长)。根据我的个人经验，即使您在执行期间只添加“几个”操作，这也可能导致极度缓慢。

请注意，tf.assign 与其他操作一样是一个操作。您应该预先定义一次(在创建模型/构建图形时)，然后在启动 session 后重复运行相同的操作。

我不知道您究竟想在您的代码片段中实现什么，但请考虑以下几点:

... 
with tf.Session() as sess: 
    sess.run(tf.assign(some_var, a_value)) 

可以替换为

a_placeholder = tf.placeholder(type_for_a_value, shape_for_a_value) 
assign_op = tf.assign(some_var, a_placeholder) 
... 
with tf.Session() as sess: 
    sess.run(assign_op, feed_dict={a_placeholder: a_value}) 

其中 a_placeholder 应该与 some_var 具有相同的 dtype/shape。我必须承认我还没有测试过这段代码，所以如果有问题请告诉我，但这应该是正确的。