【发布时间】：2017-02-01 12:17:00
【问题描述】：
我是 TF 新手：我从 MNIST 上的本教程中获取了感知器的代码（实际上，没有必要点击此链接）：https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/multilayer_perceptron.py
我想将这些感知器重新制作为具有 1 层和线性激活函数的感知器，使其成为最简单的形式：输出 =w2(w1*x+b1)+b2。但这就是我得到的：
数据：
X_train: 数组([[ 10.],
[10.],
[11.],
[6.],
[8.],
[9.],
[22.],
[14.],
[6.],
[8.],
[11.],
[9.],
[13.],
[7.],
[13.],
[7.],
[13.],
[11.]])
y_train: 数组([[ 44.5825],
[53.99]，
[52.4475]，
[37.6]，
[38.6125]，
[39.5875]，
[43.07]，
[74.8575]，
[34.185]，
[38.61]，
[34.8175]，
[36.61]，
[34.0675]，
[37.67]，
[49.725]，
[79.4775]，
[50.41]，
[51.26]])
X_test: 数组([[ 6.],
[14.],
[14.],
[12.],
[13.],
[13.]])
y_test: 数组([[ 55.75 ],
[33.035]，
[38.3275]，
[39.2825]，
[50.7325]，
[45.2575]])
参数：
learning_rate = 1
training_epochs = 1
display_step = 1 #maintaining variable
x = tf.placeholder("float", [None, 1])
y = tf.placeholder("float", [None, 1])
感知器模型：
def multilayer_perceptron(x, weights, biases, output_0):
layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
out_layer = tf.add(tf.matmul(layer_1, weights['out']), biases['out'])
output_o = out_layer #This variable is just needed to print result in session
return out_layer
output_0 = tf.Variable(tf.random_normal([1, n_classes]))
weights = {
'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes]))}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'out': tf.Variable(tf.random_normal([n_classes]))}
让我们构建图表：
prediction = multilayer_perceptron(x, weights, biases, output)
cost = tf.reduce_mean(tf.square(prediction-y)) #MSE
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) #Gives the smallest cost
init = tf.initialize_all_variables()
最后，让我们运行会话：
with tf.Session() as Sess:
Sess.run(init)
for epoch in range(training_epochs):
avg_cost = 0.
number_of_bathces = len(X_train)/batch_size
_, c = Sess.run([optimizer, cost], feed_dict = {x: X_train, y: y_train})
avg_cost += c/len(X_train)
print(Sess.run(output_0))
if epoch % display_step ==0:
print("Epoch:", '%02d' % (epoch+1), "cost =", "{:.9f}".format(avg_cost))
print("Optimization finished")
correct_prediction = tf.equal(tf.arg_max(prediction,1), tf.arg_max(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("Accuracy:", accuracy.eval({x:X_test, y:y_test}))
现在，我们得到了输出：
[[ 0.77995574]]
Epoch: 01 cost = 262.544189453
Optimization finished
Accuracy: 1.0
最令人困惑的是输出（第一个数字）！它应该在 [30; 50]！请解释一下，我哪里做错了。
【问题讨论】：
标签： machine-learning tensorflow perceptron