TensorFlow：使用自己的数据集实现单层感知器/多层感知器

Question

我是TensorFlow 的新手。我寻找了使用 tensorflow 实现多层感知器的示例，但我只 得到了关于 MNIST 图像数据集的示例，除了 MNIST 之外，我能否使用相同的优化和成本函数构建神经网络模型并训练数据数字格式，意思是，我可以使用 tensorflow 训练我自己的数字数据集吗？

有没有训练新数据集的例子？.

Answer 1

最后我明白了。使用带有 tensorflow、numpy、matplotlib 包的单层感知器构建、训练和最小化人工神经网络的成本/损失。数据以数组的形式使用，而不是MNIST。这是代码。

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
learning_rate = 0.0008
training_epochs = 2000
display_step = 50
# taking input as array from numpy package and converting it into tensor
inputX = np.array([[  2,   3],
                  [  1,   3]])
inputY = np.array([[  2,   3],
                  [  1,   3]])
x = tf.placeholder(tf.float32, [None, 2])
y_ = tf.placeholder(tf.float32, [None, 2])

W = tf.Variable([[0.0,0.0],[0.0,0.0]])
b = tf.Variable([0.0,0.0])

layer1 = tf.add(tf.matmul(x, W), b)
y = tf.nn.softmax(layer1)

cost = tf.reduce_sum(tf.pow(y_-y,2))

optimizer =tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cost)

init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

avg_set = []
epoch_set = []

for i in range(training_epochs):
   sess.run(optimizer, feed_dict = {x: inputX, y_:inputY})

   #log training
   if i % display_step == 0:
       cc = sess.run(cost, feed_dict = {x: inputX, y_:inputY})
       #check what it thinks when you give it the input data
       print(sess.run(y, feed_dict = {x:inputX}))


       print("Training step:", '%04d' % (i), "cost=", "{:.9f}".format(cc))
       avg_set.append(cc)
       epoch_set.append(i + 1)

print("Optimization Finished!")
training_cost = sess.run(cost, feed_dict = {x: inputX, y_: inputY})
print("Training cost = ", training_cost, "\nW=", sess.run(W),
      "\nb=", sess.run(b))
plt.plot(epoch_set,avg_set,'o',label = 'SLP Training phase')
plt.ylabel('cost')
plt.xlabel('epochs')
plt.legend()
plt.show()

后来通过添加隐藏层也可以用多层感知器来实现