我是Tensorflow的新手。我试图在一个1D卷积层之后添加一个最大池化层：

import tensorflow as tfimport mathsess = tf.InteractiveSession()length=458# These will be inputs## Input pixels, image with one channel (gray)x = tf.placeholder("float", [None, length])# Note that -1 is for reshapingx_im = tf.reshape(x, [-1,length,1])## Known labels# None works during variable creation to be# unspecified sizey_ = tf.placeholder("float", [None,2])# Conv layer 1num_filters1 = 2winx1 = 3W1 = tf.Variable(tf.truncated_normal(    [winx1, 1 , num_filters1],    stddev=1./math.sqrt(winx1)))b1 = tf.Variable(tf.constant(0.1,                shape=[num_filters1]))#  convolution, pad with zeros on edgesxw = tf.nn.conv1d(x_im, W1,                  stride=5,                  padding='SAME')h1 = tf.nn.relu(xw + b1)#  Max pooling, no padding on edgesp1 = tf.nn.max_pool(h1, ksize=[1, 1, 2, 1],        strides=[1, 1, 1, 1], padding='VALID')

但是我遇到了错误，我不明白为什么会这样？

回答：

tf.nn.max_pool 用于2D池化，即它期望输入张量的秩为4（你的输入张量秩是3）。你应该扩展输入的维度，或者直接使用 tf.layers.max_pooling1d：

p1 = tf.layers.max_pooling1d(h1, pool_size=2, strides=1, padding='VALID')