我想在Tensorflow中打印所有变量和占位符

时间:2016-11-06 06:39:58

标签: tensorflow

我运行示例代码recurrent_network.py

我希望打印所有x,它是一个安置者。在函数中: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)

1 个答案:

答案 0 :(得分:0)

有关详细信息,请参阅此wsgi-request-logger。我通常自己使用post