tensorflow 保存模型预测测试集分类结果

谁践踏了优雅 2022-06-12 09:21 311阅读 0赞

## Mnist分类模型—保存训练模型并参与预测测试集 ##

这篇文档开始讲解利用mnist语料集做的例子来熟悉保存训练模型的参数用来做预测，首先会出贴出保存模型的案例代码，然后会贴出预测的代码。

### 1. 训练模型 ###

# encoding=utf-8
    
    from __future__ import print_function
    
    import tensorflow as tf
    
    # Import MNIST data
    from tensorflow.examples.tutorials.mnist import input_data
    mnist = input_data.read_data_sets("./MNIST_data", one_hot=True)
    
    # Parameters
    learning_rate = 0.001
    training_iters = 128*10*300 
    batch_size = 128
    display_step = 10
    
    # Network Parameters
    n_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 input
    x = 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 simplicity
    def 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 model
    def 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 & bias
    weights = {
        # 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 model
    pred = conv_net(x, weights, biases, keep_prob)
    
    # Define loss and optimizer
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
    optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
    
    # Evaluate model
    correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
    
    # Initializing the variables
    init = tf.global_variables_initializer()
    
    saver = tf.train.Saver()  ##保存的API
    # Launch the graph
    with 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,"./Test_MNIST_model.ckpt")  #保存模型
        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. 读取模型来预测语料集的分类结果 ###

# encoding=utf-8
    from __future__ import print_function
    import tensorflow as tf
    # Import MNIST data
    from tensorflow.examples.tutorials.mnist import input_data
    mnist = input_data.read_data_sets("./MNIST_data", one_hot=True)
    
    # Parameters
    learning_rate = 0.001
    training_iters = 128*10*300 
    batch_size = 128
    display_step = 10
    
    # Network Parameters
    n_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 input
    x = 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 simplicity
    def 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 model
    def 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 & bias
    weights = {
        # 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 model
    pred = conv_net(x, weights, biases, keep_prob)
    #注意这里的变化，上面pred得到的是10个类每个类的概率值，概率值最高说明这个类就是预测的类，坐标对应0-9，所以利用下面这行代码，将预测值输出出来，tf.argmax方法是将每行向量中值最高的下标返回过来，这个下标对应的也就是类别。
    pred_class_index=tf.argmax(pred, 1)
    # # Evaluate model
    correct_pred = tf.equal(pred_class_index, tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
    
    # Initializing the variables
    init = tf.global_variables_initializer()
    
    saver = tf.train.Saver()  ##保存的API
    # Launch the graph
    with tf.Session() as sess:
        #sess.run(init) #不使用训练好的参数
        load_path = saver.restore(sess,"./Test_MNIST_model.ckpt")  #load上一步训练的参数
        step = 1
        # Keep training until reach max iterations
        batch_x=mnist.test.images[:256]
        batch_y=mnist.test.labels[:256]
        print ("batch_y:",batch_y)
        # Calculate batch loss and accuracy
        pred_value = sess.run([pred_class_index], feed_dict={x: batch_x, y: batch_y,keep_prob: 1.})
        print("pred_value:",pred_value)
        # Calculate accuracy for 256 mnist test images
        # mnist部分测试数据集，用刚刚训练好的模型来做预测。
        print("Testing Accuracy:", \
            sess.run(accuracy, feed_dict={x: mnist.test.images[:256],
                                          y: mnist.test.labels[:256],
                                          keep_prob: 1.}))

代码运行环境是tf-1.2，Linux环境，运行成功，大家有问题欢迎评论留言