TensorFlow the model and load the model to make predictions (no need to redefine the network structure)

below, an offline regression model is used to record the saving model and load model to make predictions . Reference Articles:http://blog.csdn.net/thriving_fcl/article/details/71423039

train an offline regression model and save a look at the code:

Import TensorFlow as TF import numpy as NP import Matplotlib.pyplot as Plt Money=np.array ([[[109],[82],[99], [72], [87], [ [To], [to], [Astype], [+]]. Np.float32 Click=np.array ([[One], [8], [8], [6],[7], [7], [7], [8], [9], [5]]). Astyp E (Np.float32) x_test=money[0:5].reshape ( -1,1) y_test=click[0:5] X_train=money[5:].reshape ( -1,1) y_train=click[5:] X =tf.placeholder (tf.float32,[none,1],name= ' x ') #保存要输入的格式 W=TF. Variable (Tf.zeros ([1,1])) B=TF. Variable (Tf.zeros ([1])) Y=tf.matmul (x,w) +b tf.add_to_collection (' pred_network ', y) #用于加载模型获取要预测的网络结构 y_= Tf.placeholder (tf.float32,[none,1]) cost=tf.reduce_sum (Tf.pow ((Y-y_), 2)) train_step= Tf.train.GradientDescentOptimizer (0.000001). Minimize (cost) Init=tf.global_variables_initializer () sess=tf. Session () Sess.run (init) cost_history=[] saver = Tf.train.Saver () to I in range (MB): Feed={x:x_train,y_:y_train} SESS.R Un (train_step,feed_dict=feed) cost_history.append (Sess.run (cost,feed_dict=feed)) # outputs the final w,b and cost value of print ("109 of the predicted value is: ", Sess.run (Y, Feed_dICT={X: [[[109]]}) Print ("W_value:%f"% Sess.run (W), "B_value:%f"% Sess.run (b), "Cost_value:%f"% sess.run (cost, Feed_ dict=feed)) Saver_path = Saver.save (Sess, "/users/shuubiasahi/desktop/tensorflow/mod