TensorFlow:在 fn 中创建变量tf.map_fn返回值错误

Question

我对map_fn中的变量初始化有疑问。

我试图在张量中的每个元素上分别应用一些高速公路层，所以我认为map_fn可能是最好的方法。

segment_list = tf.reshape(raw_segment_embedding,[batch_size*seqlen,embed_dim])
segment_embedding = tf.map_fn(lambda x: stack_highways(x, hparams), segment_list)

现在的问题是我的fn，即stack_highways创建变量，并且由于某种原因，tensorflow无法初始化这些变量并给出此错误。

W = tf.Variable(tf.truncated_normal(W_shape, stddev=0.1), name='weight')
ValueError: Initializer for variable body/model/parallel_0/body/map/while/highway_layer0/weight/ is from inside a control-flow construct, such as a loop or conditional. When creating a variable inside a loop or conditional, use a lambda as the initializer. 

我现在很无知，基于错误，我想这与范围无关，但我不知道如何使用 lambda 作为初始值设定项(我什至不知道这到底是什么意思(。 以下是stack_highways的实施，任何建议将不胜感激。

def weight_bias(W_shape, b_shape, bias_init=0.1):
"""Fully connected highway layer adopted from 
https://github.com/fomorians/highway-fcn/blob/master/main.py
"""
W = tf.Variable(tf.truncated_normal(W_shape, stddev=0.1), name='weight')
b = tf.Variable(tf.constant(bias_init, shape=b_shape), name='bias')
return W, b


def highway_layer(x, size, activation, carry_bias=-1.0):
"""Fully connected highway layer adopted from 
https://github.com/fomorians/highway-fcn/blob/master/main.py
"""
W, b = weight_bias([size, size], [size])
with tf.name_scope('transform_gate'):
W_T, b_T = weight_bias([size, size], bias_init=carry_bias)

H = activation(tf.matmul(x, W) + b, name='activation')
T = tf.sigmoid(tf.matmul(x, W_T) + b_T, name='transform_gate')
C = tf.sub(1.0, T, name="carry_gate")

y = tf.add(tf.mul(H, T), tf.mul(x, C), name='y') # y = (H * T) + (x * C)
return y


def stack_highways(x, hparams):
"""Create highway networks, this would not create
a padding layer in the bottom and the top, it would 
just be layers of highways.

Args:
x: a raw_segment_embedding
hparams: run hyperparameters

Returns:
y: a segment_embedding
"""
highway_size = hparams.highway_size
activation = hparams.highway_activation #tf.nn.relu
carry_bias_init = hparams.highway_carry_bias
prev_y = None
y = None
for i in range(highway_size):
with tf.name_scope("highway_layer{}".format(i)) as scope:
if i == 0: # first, input layer
prev_y = highway_layer(x, highway_size, activation, carry_bias=carry_bias_init)
elif i == highways - 1: # last, output layer
y = highway_layer(prev_y, highway_size, activation, carry_bias=carry_bias_init)
else: # hidden layers
prev_y = highway_layer(prev_y, highway_size, activation, carry_bias=carry_bias_init)
return y

最热烈的问候， 科尔曼

Answer 1

TensorFlow 提供了两种初始化变量的主要方法：

1. "lambda"初始值设定项：返回初始化值的可调用对象。TF提供了许多包装精美的产品。
2. 通过张量值初始化：这是您当前使用的。

错误消息指出，在使用while_loop中的变量(map_fn内部调用(时，需要使用第一种类型的初始值设定项。(一般来说，lambda 初始值设定项对我来说似乎更健壮。

此外，在过去，tf.get_variable似乎比 tf 更受欢迎。从控制流中使用时可变。

因此，我怀疑您可以通过将weight_bias功能修复为以下内容来解决您的问题：

def weight_bias(W_shape, b_shape, bias_init=0.1):
"""Fully connected highway layer adopted from 
https://github.com/fomorians/highway-fcn/blob/master/main.py
"""
W = tf.get_variable("weight", shape=W_shape,
initializer=tf.truncated_normal_initializer(stddev=0.1))
b = tf.get_variable("bias", shape=b_shape,
initializer=tf.constant_inititializer(bias_init))
return W, b

希望对您有所帮助！