【问题标题】:ValueError: Cannot feed value of shape (200,) for Tensor 'Placeholder_32:0', which has shape '(?, 1)'ValueError:无法为具有形状“(?,1)”的张量“Placeholder_32:0”提供形状(200,)的值
【发布时间】:2018-04-29 01:16:49
【问题描述】:

我是张量流的新手。此代码仅适用于简单的神经网络。 我认为问题可能来自:

x_data = np.linspace(-0.5,0.5,200)[:np..newaxis]

我尝试在没有[:np.newaxis] 的情况下编写,但看起来一样。

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

x_data = np.linspace(-0.5,0.5,200)[:np.newaxis]
noise = np.random.normal(0,0.02,x_data.shape)
y_data = np.square(x_data) + noise

x = tf.placeholder(tf.float32,[None,1])
y = tf.placeholder(tf.float32,[None,1])

Weights_L1 = tf.Variable(tf.random_normal([1,10]))
biases_L1 = tf.Variable(tf.zeros([1,10]))
Wx_plus_b_L1 = tf.matmul(x,Weights_L1) + biases_L1
L1 = tf.nn.tanh(Wx_plus_b_L1)

Weights_L2 = tf.Variable(tf.random_normal([10,1]))
biases_L2 = tf.Variable(tf.zeros([1,1]))
Wx_plus_b_L2 = tf.matmul(L1,Weights_L2) + biases_L2
prediction = tf.nn.tanh(Wx_plus_b_L2)

loss = tf.reduce_mean(tf.square(y-prediction))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for _ in range(2000):
        sess.run(train_step,feed_dict={x:x_data,y:y_data})

    prediction_value = sess.run(prediction,feed_dict={x:x_data})
    plt.figure()
    plt.scatter(x_data,y_data)
    plt.plot(x_data,prediction_value,'r-',lw=5)
    plt.show()

【问题讨论】:

    标签: python numpy machine-learning tensorflow neural-network


    【解决方案1】:

    定义的占位符(xy)是二维的,因此您应该将输入数组重新整形为排名 2。尝试添加以下内容:

    x_data = x_data.reshape([-1,1])
    y_data = y_data.reshape([-1,1])
    

    【讨论】:

      猜你喜欢
      • 2018-08-03
      • 2020-03-27
      • 2021-07-01
      • 1970-01-01
      • 2020-11-18
      • 1970-01-01
      • 2018-12-15
      • 1970-01-01
      • 2022-01-09
      相关资源
      最近更新 更多