python中tf.abs_python – Tensorflow：替换tf.nn.rnn_cell._linear(输入,大小,0,范围)

我试图从

https://arxiv.org/pdf/1609.05473.pdf开始运行SequenceGAN(

https://github.com/LantaoYu/SeqGAN).

修复明显的错误后,比如用堆栈替换pack,它仍然无法运行,因为高速公路网络部分需要tf.nn.rnn_cell._linear函数：

# highway layer that borrowed from https://github.com/carpedm20/lstm-char-cnn-tensorflow

def highway(input_, size, layer_size=1, bias=-2, f=tf.nn.relu):

"""Highway Network (cf. http://arxiv.org/abs/1505.00387).

t = sigmoid(Wy + b)

z = t * g(Wy + b) + (1 - t) * y

where g is nonlinearity, t is transform gate, and (1 - t) is carry gate.

"""

output = input_

for idx in range(layer_size):

output = f(tf.nn.rnn_cell._linear(output, size, 0, scope='output_lin_%d' % idx)) #tf.contrib.layers.linear instad doesn't work either.

transform_gate = tf.sigmoid(tf.nn.rnn_cell._linear(input_, size, 0, scope='transform_lin_%d' % idx) + bias)

carry_gate = 1. - transform_gate

output = transform_gate * output + carry_gate * input_

return output

在Tensorflow 1.0或0.12中,tf.nn.rnn_cell._linear函数似乎不再存在,我不知道要用什么替换它.我找不到任何新的实现,或者有关tensorflow的github或(遗憾的是非常稀疏的)文档的任何信息.

有人知道这个功能的新吊坠吗？

非常感谢提前！