深度学习实战篇之 ( 十四) -- TensorFlow之VGG16

def inference(images, batch_size, n_classes,drop_rate):
    # 一个简单的卷积神经网络，卷积+池化层x2，全连接层x2，最后一个softmax层做分类。
    # 卷积层1
    # 1. 64通道卷积层块: 输入: 224x224x3, 2层3x3x64的卷积结构, padding, 输出：64x224x224
    # 2. maxpooling1：输入: 64x224x224, 输出: 112x112x64
    conv1 = Conv_layer(names = 'conv_block1', input = images , w_shape = [3, 3, 3, 64], b_shape = [64], strid = [1, 1])
    conv2 = Conv_layer(names = 'conv_block2', input = conv1 , w_shape = [3, 3, 64, 64], b_shape = [64], strid = [1, 1])
    pool_1 = Max_pool_lrn(names = 'pooling1', input = conv2 , ksize = [1, 2, 2, 1], is_lrn = True)

    # 3. 128通道卷积块：输入: 64x112x1122, 2层3x3x128的卷积结构, padding，输出：128x112x112
    # 4. maxpooling2: 输入: 128x112x112, 输出: 128x56x56
    conv3 = Conv_layer(names = 'conv_block3', input = pool_1 , w_shape = [3, 3, 64, 128], b_shape = [128], strid = [1, 1])
    conv4 = Conv_layer(names = 'conv_block4', input = conv3 , w_shape = [3, 3, 128, 128], b_shape = [128], strid = [1, 1])
    pool_2 = Max_pool_lrn(names = 'pooling2', input = conv4 , ksize = [1, 2, 2, 1], is_lrn = False)

    # 5. 256通道卷积块：输入: 128x56x56, 3层3x3x256的卷积结构, padding, 输出：256x56x56。
    # 6. maxpooling3: 输入: 256x56x56, 输出: 256x28x28
    
    conv5 = Conv_layer(names = 'conv_block5', input = pool_2 , w_shape = [3, 3, 128, 256], b_shape = [256], strid = [1, 1])
    conv6 = Conv_layer(names = 'conv_block6', input = conv5 , w_shape = [3, 3, 256, 256], b_shape = [256], strid = [1, 1])
    conv7 = Conv_layer(names = 'conv_block7', input = conv6 , w_shape = [3, 3, 256, 256], b_shape = [256], strid = [1, 1])
    pool_3 = Max_pool_lrn(names = 'pooling3', input = conv7 , ksize = [1, 2, 2, 1], is_lrn = False)

    # 7. 512通道卷积块: 输入: 256x28x28, 3层3x3x512的卷积结构, padding, 输出：512x28x28。
    # 8  maxpooling4: 输入：512x28x28, 输出：512x14x14。
    conv8 = Conv_layer(names = 'conv_block8', input = pool_3 , w_shape = [3, 3, 256, 512], b_shape = [512], strid = [1, 1])
    conv9 = Conv_layer(names = 'conv_block9', input = conv8 , w_shape = [3, 3, 512, 512], b_shape = [512], strid = [1, 1])
    conv10 = Conv_layer(names = 'conv_block10', input = conv9 , w_shape = [3, 3, 512, 512], b_shape = [512], strid = [1, 1])
    pool_4 = Max_pool_lrn(names = 'pooling4', input = conv10 , ksize = [1, 2, 2, 1], is_lrn = False)
    # print(pool_4.shape)

    # 9. 512通道卷积块: 输入: 512x14x14, 3层3x3x512的卷积结构, padding, 输出：512x14x14。
    # 10. maxpooling4: 输入：512x14x14, 输出：512x7x7。
    conv11 = Conv_layer(names = 'conv_block11', input = pool_4 , w_shape = [3, 3, 512, 512], b_shape = [512], strid = [1, 1])
    conv12 = Conv_layer(names = 'conv_block12', input = conv11 , w_shape = [3, 3, 512, 512], b_shape = [512], strid = [1, 1])
    conv13 = Conv_layer(names = 'conv_block13', input = conv12 , w_shape = [3, 3, 512, 512], b_shape = [512], strid = [1, 1])
    pool_5 = Max_pool_lrn(names = 'pooling5', input = conv13 , ksize = [1, 2, 2, 1], is_lrn = False)

    # 11. 全连接层1：输入:512*7*7，输出:4096
    # 12. 全连接层1：输入:4096，输出:4096
    # 13. 全连接层1：输入:4096，输出:5(类别数目)
    reshape = tf.reshape(pool_5, shape=[batch_size, -1])
    dim = reshape.get_shape()[1].value

    local_1 = local_layer(names = 'local1_scope', input = reshape , w_shape = [dim, 4096], b_shape = [4096])
    local_2 = local_layer(names = 'local2_scope', input = local_1 , w_shape = [4096, 4096], b_shape = [4096])

    with tf.variable_scope('softmax_linear') as scope:
        weights = tf.Variable(tf.truncated_normal(shape=[4096, n_classes], stddev=0.005, dtype=tf.float32),
                              name='softmax_linear', dtype=tf.float32)

        biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[n_classes]),
                             name='biases', dtype=tf.float32)

        softmax_linear = tf.add(tf.matmul(local_2, weights), biases, name='softmax_linear')
        # print("---------softmax_linear:{}".format(softmax_linear))

    return softmax_linear