import tensorflow as tf import numpy as np import matplotlib.pyplot as plt #Random generation layer 200 random points between -0.5 and 0.5 200 x_data = e.g. linspace (-0.5,0.5,200) [:, e.g. newaxis] noise=np.random.normal(0,0.02,x_data.shape) y_data=np.square(x_data)+noise #[None,1] Undetermined number of rows, one column x=tf.placeholder(tf.float32,[None,1]) y=tf.placeholder(tf.float32,[None,1]) #define middle layer #one row 10 columns 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) #excitation function #define output layer 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) #Get the predicted value excitation function #Secondary cost function loss=tf.reduce_mean(tf.square(y-prediction)) #train with gradient descent optimizer 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}) # get the predicted value prediction_value=sess.run(prediction,feed_dict={x:x_data}) plt.figure() plt.scatter(x_data,y_data) #'r-' red solid line lw=5 width is 5 plt.plot(x_data,prediction_value,'r-',lw=5) plt.show()
TensorFlow (example + prediction) template
Guess you like
Origin http://43.154.161.224:23101/article/api/json?id=324641986&siteId=291194637
Ranking