基于Tensorflow的机器学习(5) -- 全连接神经网络

这篇博客将实现的主要神经网络如下所示：

以下是相关代码的实现步骤：

简单化的实现

导入必要内容

# Import MNIST dataimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

参数初始化

# Parameterslearning_rate = 0.1num_steps = 500batch_size = 128display_step = 100# Network Parametersn_hidden_1 = 256 # 1st layer number of neuronsn_hidden_2 = 256 # 2nd layer number of neuronsnum_input = 784 # MNIST data input (img shape: 28*28)num_classes = 10 # MNIST total classes (0-9 digits)# tf Graph InputX = tf.placeholder("float", [None, num_input])Y = tf.placeholder("float", [None, num_classes])

此处每个隐藏层都有256个神经元，输入是通过图片转换而来的784维数组，一共将所有数据分为0-9这10个类。

存储weights 和 bias

# Store layers weight & biasweights = {    'h1' : tf.Variable(tf.random_normal([num_input, n_hidden_1])),    'h2' : tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),    'out' : tf.Variable(tf.random_normal([n_hidden_2, num_classes]))}# 为何我们要将上述的两个变量以矩阵的形式进行传输biases = {    'b1' : tf.Variable(tf.random_normal([n_hidden_1])),    'b2' : tf.Variable(tf.random_normal([n_hidden_2])),    'out' : tf.Variable(tf.random_normal([num_classes]))}

模型创建

# Create modeldef neural_net(x):    # Hidden fully connnected layer with 256 neurons    layer_1 = tf.add(tf.matmul(x, weights['h1']) , biases['b1'])    # Hidden fully connnected layer with 256 neurons    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']) , biases['b2'])    # Output fully connected layer with a neuron for each class    out_layer = tf.matmul(layer_2, weights['out']) + biases['out']    return out_layer

模型构建

# Create modeldef neural_net(x):    # Hidden fully connnected layer with 256 neurons    layer_1 = tf.add(tf.matmul(x, weights['h1']) , biases['b1'])    # Hidden fully connnected layer with 256 neurons    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']) , biases['b2'])    # Output fully connected layer with a neuron for each class    out_layer = tf.matmul(layer_2, weights['out']) + biases['out']    return out_layer

模型训练

# Start trainingwith tf.Session() as sess:    # Run the initilizer    sess.run(init)    for step in range(1, num_steps+1):        batch_x, batch_y = mnist.train.next_batch(batch_size)        # Run optimization op (backporp)        sess.run(train_op, feed_dict={X: batch_x, Y: batch_y})        if step % display_step == 0 or step == 1:            # Calculate batch loss and accuracy            loss, acc = sess.run([loss_op, accuracy], feed_dict={X: batch_x, Y: batch_y})            print("Step " + str(step) + ", Minibatch Loss= " + \                  "{:.4f}".format(loss) + ", Training Accuracy= " + \                  "{:.3f}".format(acc))    print("Optimization Finished!")    # Calculate accuracy for MNIST test images    print("Testiing Accuracy:", \         sess.run(accuracy, feed_dict={X: mnist.test.images, Y: mnist.test.labels}))

结果输出：

Step 1, Minibatch Loss= 10718.8223, Training Accuracy= 0.289Step 100, Minibatch Loss= 254.0072, Training Accuracy= 0.852Step 200, Minibatch Loss= 91.2099, Training Accuracy= 0.859Step 300, Minibatch Loss= 65.1114, Training Accuracy= 0.859Step 400, Minibatch Loss= 48.7690, Training Accuracy= 0.891Step 500, Minibatch Loss= 13.4156, Training Accuracy= 0.922Optimization Finished!('Testiing Accuracy:', 0.8648001)

全连接网络高级实现

以下实例将使用tensorflow的 ‘layers’ 和 ‘estimator’的API去构建上述的全连接网络。

具体实现步骤如下：

导入必要内容

# Import MNIST datafrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("/tmp/data", one_hot=False)import tensorflow as tfimport matplotlib.pyplot as pltimport numpy as np

参数初始化

# Parameterslearning_rate = 0.01num_steps = 1000batch_size = 128display_step = 100# Network Parametersn_hidden_1 = 256 # 1st layer number of neuronsn_hidden_2 = 256 # 2nd layer number of neuronsnum_input = 784 # MNIST data input( img shape: 28*28)num_classes = 10 # MNIST total classes (0-9 digits)

定义输入函数

# Define the input function for traininginput_fn = tf.estimator.inputs.numpy_input_fn(    x={'images': mnist.train.images}, y=mnist.train.labels,    batch_size=batch_size, num_epochs=None, shuffle=True)

稍后对estimator的API进行具体分析，此处只需要记住相关用法即可

定义神经网络

# Define the neural networkdef neural_net(x_dict):    # TF Estimator input is a dict, in case of multiple inputs    x = x_dict['images']    # Hidden fully connected layer with 256 neurons    layer_1 = tf.layers.dense(x, n_hidden_1)    # Hidden fully connected layer with 256 neurons    layer_2 = tf.layers.dense(layer_1, n_hidden_2)    # Output fully connected layer with a neuron for each class    out_layer = tf.layers.dense(layer_2, num_classes)    return out_layer

定义模型函数

# Define the model function (following TF Estimator Template)def model_fn(features, labels, mode):    # Build the neural network    logits = neural_net(features) # features 是个啥    # Predictions    pred_classes = tf.argmax(logits, axis=1)    pred_probas = tf.nn.softmax(logits)    # If prediction mode, early return    if mode == tf.estimator.ModeKeys.PREDICT:        return tf.estimator.EstimatorSpec(mode, predictions=pred_classes)    # Define loss and optimizer    loss_op = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(        logits=logits, labels=tf.cast(labels, dtype=tf.int32)))    optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)    train_op = optimizer.minimize(loss_op, global_step=tf.train.get_global_step())    # 什么是global step??    # Evaluate the accuracy of the model    acc_op = tf.metrics.accuracy(labels=labels, predictions=pred_classes)    # TF Estimators requires to return a EstimatorSpec, that specify    # the different ops for training, evaluating    estim_specs = tf.estimator.EstimatorSpec(        mode=mode,        predictions=pred_classes,        loss=loss_op,        train_op=train_op,        eval_metric_ops={'accuracy': acc_op})    return estim_specs

建立estimator

# Build the Estimatormodel = tf.estimator.Estimator(model_fn)

模型训练

# Train the Modelmodel.train(input_fn, steps=num_steps)

模型评估

# Evaluate the Model# Define the input function for evaluatinginput_fn = tf.estimator.inputs.numpy_input_fn(    x={'images': mnist.test.images}, y=mnist.test.labels,    batch_size=batch_size, shuffle=False)# Use the Estimator 'evaluate' methodmodel.evaluate(input_fn)

输出结果为：

{'accuracy': 0.9091, 'global_step': 2000, 'loss': 0.31571656}

单图片预测

# Predict single imagesn_images = 5# Get images from test settest_images = mnist.test.images[:n_images]# Prepare the input datainput_fn = tf.estimator.inputs.numpy_input_fn(    x={'images': test_images}, shuffle=False)# Use the model to predict the images classpreds = list(model.predict(input_fn))# Displayfor i in range(n_images):    plt.imshow(np.reshape(test_images[i], [28,28]), cmap='gray')    plt.show()    print("Model prediction: ", preds[i])

以上便是基于tensorflow的全连接网络的理论及其应用的全部内容。