Tensorflow saves and uses the training model

(1) Save the training model, name the model my_net.ckp, and save it in the net/ folder

         saver = tf.train.Saver()

         with tf.Session() as sess:

             #Save the model
             saver.save(sess,'net/my_net.ckpt')

(2) Call the local model

        saver = tf.train.Saver()

         with tf.Session() as sess:

             # call the model

            saver.restore(sess,'net/my_net.ckpt')