2016-11-06 50 views
0

我运行示例代码recurrent_network.py我想在Tensorflow中打印所有变量和占位符

我希望打印所有的x,它是一个placehoder。在功能中:RNN(x, weights, biases):

我该怎么办?

关键点:

x = tf.transpose(x, [1, 0, 2]) 
    # Reshaping to (n_steps*batch_size, n_input) 
    x = tf.reshape(x, [-1, n_input]) 
    # Split to get a list of 'n_steps' tensors of shape (batch_size, n_input) 
    x = tf.split(0, n_steps, x) 

回答