tensorflow儲存網路參數 使用訓練好的網路參數進行資料的預測

訓練好網路後，重要的是後期的再訓練和預測。所以本文主要講如果儲存訓練好的參數以及使用訓練好的參數。
主要使用的API
https://www.tensorflow.org/api_docs/python/tf/train/Saver

下面使用例子進行說明，該網路是對手寫數字構建一個卷積神經網路進行識別。

https://github.com/xgli/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/convolutional_network.py

1、儲存網路參數

1.聲明saver的API
2.儲存模型

'''A Convolutional Network implementation example using TensorFlow library.This example is using the MNIST database of handwritten digits(http://yann.lecun.com/exdb/mnist/)Author: Aymeric DamienProject: https://github.com/aymericdamien/TensorFlow-Examples/'''from __future__ import print_functionimport tensorflow as tf# Import MNIST datafrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("/tmp/data/", one_hot=True)# Parameterslearning_rate = 0.001training_iters = 128*10*3 batch_size = 128display_step = 10# Network Parametersn_input = 784 # MNIST data input (img shape: 28*28)n_classes = 10 # MNIST total classes (0-9 digits)dropout = 0.75 # Dropout, probability to keep units# tf Graph inputx = tf.placeholder(tf.float32, [None, n_input])y = tf.placeholder(tf.float32, [None, n_classes])keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)# Create some wrappers for simplicitydef conv2d(x, W, b, strides=1):    # Conv2D wrapper, with bias and relu activation    x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')    x = tf.nn.bias_add(x, b)    return tf.nn.relu(x)def maxpool2d(x, k=2):    # MaxPool2D wrapper    return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],                          padding='SAME')# Create modeldef conv_net(x, weights, biases, dropout):    # Reshape input picture    x = tf.reshape(x, shape=[-1, 28, 28, 1])    # Convolution Layer    conv1 = conv2d(x, weights['wc1'], biases['bc1'])    # Max Pooling (down-sampling)    conv1 = maxpool2d(conv1, k=2)    # Convolution Layer    conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])    # Max Pooling (down-sampling)    conv2 = maxpool2d(conv2, k=2)    # Fully connected layer    # Reshape conv2 output to fit fully connected layer input    fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])    fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])    fc1 = tf.nn.relu(fc1)    # Apply Dropout    fc1 = tf.nn.dropout(fc1, dropout)    # Output, class prediction    out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])    return out# Store layers weight & biasweights = {    # 5x5 conv, 1 input, 32 outputs    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),    # 5x5 conv, 32 inputs, 64 outputs    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),    # fully connected, 7*7*64 inputs, 1024 outputs    'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),    # 1024 inputs, 10 outputs (class prediction)    'out': tf.Variable(tf.random_normal([1024, n_classes]))}biases = {    'bc1': tf.Variable(tf.random_normal([32])),    'bc2': tf.Variable(tf.random_normal([64])),    'bd1': tf.Variable(tf.random_normal([1024])),    'out': tf.Variable(tf.random_normal([n_classes]))}# Construct modelpred = conv_net(x, weights, biases, keep_prob)# Define loss and optimizercost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)# Evaluate modelcorrect_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))# Initializing the variablesinit = tf.global_variables_initializer()saver = tf.train.Saver()  ##儲存的API# Launch the graphwith tf.Session() as sess:    sess.run(init)    step = 1    # Keep training until reach max iterations    while step * batch_size < training_iters:        batch_x, batch_y = mnist.train.next_batch(batch_size)        # Run optimization op (backprop)        sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,                                       keep_prob: dropout})        if step % display_step == 0:            # Calculate batch loss and accuracy            loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,                                                              y: batch_y,                                                              keep_prob: 1.})            print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \                  "{:.6f}".format(loss) + ", Training Accuracy= " + \                  "{:.5f}".format(acc))        step += 1    print("Optimization Finished!")    print("save model")    save_path = saver.save(sess,"./model")  #儲存模型    print("save model:{0} Finished".format(save_path))    # Calculate accuracy for 256 mnist test images    print("Testing Accuracy:", \        sess.run(accuracy, feed_dict={x: mnist.test.images[:256],                                      y: mnist.test.labels[:256],                                      keep_prob: 1.}))

2、使用儲存的網路參數

'''A Convolutional Network implementation example using TensorFlow library.This example is using the MNIST database of handwritten digits(http://yann.lecun.com/exdb/mnist/)Author: Aymeric DamienProject: https://github.com/aymericdamien/TensorFlow-Examples/'''from __future__ import print_functionimport tensorflow as tf# Import MNIST datafrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("/tmp/data/", one_hot=True)# Parameterslearning_rate = 0.001training_iters = 128*10*3 batch_size = 128display_step = 10# Network Parametersn_input = 784 # MNIST data input (img shape: 28*28)n_classes = 10 # MNIST total classes (0-9 digits)dropout = 0.75 # Dropout, probability to keep units# tf Graph inputx = tf.placeholder(tf.float32, [None, n_input])y = tf.placeholder(tf.float32, [None, n_classes])keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)# Create some wrappers for simplicitydef conv2d(x, W, b, strides=1):    # Conv2D wrapper, with bias and relu activation    x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')    x = tf.nn.bias_add(x, b)    return tf.nn.relu(x)def maxpool2d(x, k=2):    # MaxPool2D wrapper    return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],                          padding='SAME')# Create modeldef conv_net(x, weights, biases, dropout):    # Reshape input picture    x = tf.reshape(x, shape=[-1, 28, 28, 1])    # Convolution Layer    conv1 = conv2d(x, weights['wc1'], biases['bc1'])    # Max Pooling (down-sampling)    conv1 = maxpool2d(conv1, k=2)    # Convolution Layer    conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])    # Max Pooling (down-sampling)    conv2 = maxpool2d(conv2, k=2)    # Fully connected layer    # Reshape conv2 output to fit fully connected layer input    fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])    fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])    fc1 = tf.nn.relu(fc1)    # Apply Dropout    fc1 = tf.nn.dropout(fc1, dropout)    # Output, class prediction    out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])    return out# Store layers weight & biasweights = {    # 5x5 conv, 1 input, 32 outputs    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),    # 5x5 conv, 32 inputs, 64 outputs    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),    # fully connected, 7*7*64 inputs, 1024 outputs    'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),    # 1024 inputs, 10 outputs (class prediction)    'out': tf.Variable(tf.random_normal([1024, n_classes]))}biases = {    'bc1': tf.Variable(tf.random_normal([32])),    'bc2': tf.Variable(tf.random_normal([64])),    'bd1': tf.Variable(tf.random_normal([1024])),    'out': tf.Variable(tf.random_normal([n_classes]))}# Construct modelpred = conv_net(x, weights, biases, keep_prob)# Define loss and optimizercost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)# Evaluate modelcorrect_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))# Initializing the variablesinit = tf.global_variables_initializer()saver = tf.train.Saver()  ##儲存的API# Launch the graphwith tf.Session() as sess:    #sess.run(init) #不使用訓練好的參數    load_path = saver.restore(sess,"./model")  #load上一步訓練的參數    step = 1    # Keep training until reach max iterations    while step * batch_size < training_iters:        batch_x, batch_y = mnist.train.next_batch(batch_size)        # Run optimization op (backprop)        sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,                                       keep_prob: dropout})        if step % display_step == 0:            # Calculate batch loss and accuracy            loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,                                                              y: batch_y,                                                              keep_prob: 1.})            print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \                  "{:.6f}".format(loss) + ", Training Accuracy= " + \                  "{:.5f}".format(acc))        step += 1    print("Optimization Finished!")    print("save model")    save_path = saver.save(sess,"./model")  #儲存模型    print("save model:{0} Finished".format(save_path))    # Calculate accuracy for 256 mnist test images    print("Testing Accuracy:", \        sess.run(accuracy, feed_dict={x: mnist.test.images[:256],                                      y: mnist.test.labels[:256],                                      keep_prob: 1.}))