參考黃文堅《TensorFlow實戰》一書，完成AlexNet的整體實現並展望其訓練和預測過程。

import tensorflow as tf

batch_size = 32
num_batches = 100


# 顯示網絡每一層結構，展示每一個卷積層或池化層輸出tensor的尺寸,接受一個tensor作為輸入
def print_activations(t):
    print(t.op.name, ‘ ‘, t.get_shape().as_list())


# 接受images作為輸入，返回最後一層pool5（第五個池化層）
# 及parameters(AlexNet中所有需要訓練的模型參數)‘‘‘
 

def inference(images):
    parameters = []

    with tf.name_scope(‘conv1‘) as scope:
        # 用截斷的正態分布函數（標準差為0.1）初始化卷積核的參數kernel。卷積核尺寸為11*11，顏色通道為3，卷積核數量為64
        kernel = tf.Variable(tf.truncated_normal([11, 11, 3, 64],
                    dtype=tf.float32, stddev=1e-1), name=‘weights‘)
        
 
# 使用tf.nn.conv2d對輸入images完成卷積操作
        conv = tf.nn.conv2d(images, kernel, [1, 4, 4, 1], padding=‘SAME‘)
        biases = tf.Variable(tf.constant(0.0, shape=[64], dtype=tf.float32),
                             trainable=True, name=‘biases‘)
        bias = tf.nn.bias_add(conv, biases)
        conv1 = tf.nn.relu(bias, name=scope)
        print_activations(conv1)
        parameters 
 
+= [kernel, biases]
    # LRN處理和最大池化處理
    lrn1 = tf.nn.lrn(conv1, 4, bias=1.0, alpha=0.001/9, beta=0.75, name=‘lrn1‘)
    pool1 = tf.nn.max_pool(lrn1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
                           padding=‘VALID‘, name=‘pool1‘)
    print_activations(pool1) # 打印輸出結果pool1的結構

    # 設計第二個卷積層 卷積核尺寸5*5 輸入通道數64 卷積核數量192
    with tf.name_scope(‘conv2‘) as scope:
        kernel = tf.Variable(tf.truncated_normal([5, 5, 64, 192],
                                                 dthpe=tf.float32, stddev=1e-1), name=‘weights‘)
        # 卷積步長全部設為1,即掃描全圖像素
        conv = tf.nn.conv2d(pool1, kernel, [1, 1, 1, 1], padding=‘SAME‘)
        biases = tf.Variable(tf.constant(0.0, shape=[192], dtype=tf.float32),
                             trainable=True, name=‘biases‘)
        bias = tf.nn.bias_add(conv, biases)
        conv2 = tf.nn.relu(bias, name=scope)
        parameters += [kernel, biases]
        print_activations(conv2)

    lrn2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001/9, beta=0.75, name=‘lrn2‘)
    pool2 = tf.nn.max_pool(lrn2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
                           padding=‘VALID‘, name=‘pool2‘)
    print_activations(pool2)

    # 創建第三個卷積層 卷積核尺寸3*3 輸入通道數192 卷積核數量384 步長全為1
    with tf.name_scope(‘conv3‘) as scope:
        kernel = tf.Variable(tf.truncated_normal([3, 3, 192, 384],
                                                 dthpe=tf.float32, stddev=1e-1), name=‘weights‘)
        # 卷積步長全部設為1,即掃描全圖像素
        conv = tf.nn.conv2d(pool2, kernel, [1, 1, 1, 1], padding=‘SAME‘)
        biases = tf.Variable(tf.constant(0.0, shape=[384], dtype=tf.float32),
                             trainable=True, name=‘biases‘)
        bias = tf.nn.bias_add(conv, biases)
        conv3 = tf.nn.relu(bias, name=scope)
        parameters += [kernel, biases]
        print_activations(conv3)

    # 創建第四個卷積層 卷積核尺寸3*3 輸入通道數384 卷積核數量降為256
    with tf.name_scope(‘conv4‘) as scope:
        kernel = tf.Variable(tf.truncated_normal([3, 3, 384, 256],
                                                 dthpe=tf.float32, stddev=1e-1), name=‘weights‘)
        # 卷積步長全部設為1,即掃描全圖像素
        conv = tf.nn.conv2d(conv3, kernel, [1, 1, 1, 1], padding=‘SAME‘)
        biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
                             trainable=True, name=‘biases‘)
        bias = tf.nn.bias_add(conv, biases)
        conv4 = tf.nn.relu(bias, name=scope)
        parameters += [kernel, biases]
        print_activations(conv4)

        # 最後的第五個卷積層 卷積核尺寸3*3 輸入通道數256 卷積核數量為256
        with tf.name_scope(‘conv5‘) as scope:
            kernel = tf.Variable(tf.truncated_normal([3, 3, 256, 256],
                                                     dthpe=tf.float32, stddev=1e-1), name=‘weights‘)
            # 卷積步長全部設為1,即掃描全圖像素
            conv = tf.nn.conv2d(conv4, kernel, [1, 1, 1, 1], padding=‘SAME‘)
            biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
                                 trainable=True, name=‘biases‘)
            bias = tf.nn.bias_add(conv, biases)
            conv5 = tf.nn.relu(bias, name=scope)
            parameters += [kernel, biases]
            print_activations(conv5)

        # 在5個卷積層之後，還有一個最大池化層，這個池化層和前兩個卷積層後的池化層一致
        pool5 = tf.nn.max_pool(conv5, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
                               padding=‘VALID‘, name=‘pool5‘)
        print_activations(pool5)

        return pool5, parameters
        # 在正式使用AlexNet來訓練或預測時，還需要添加3個全連接層，隱含節點數分別為4096、4096、1000

後續形成實現卷積神經網絡構建、訓練、測試的代碼架構，會將Alexnet實現結構重新組織完整和優化。

tensorFlow入門實踐（三）初識AlexNet實現結構