深度学习-卷积神经网络-经典的卷积网络incepttion-ResNet-DenceNet-46

• 1. Inception
• 2. ResNet
• 3. DenseNet
• 4. MobileNet

1. Inception

其中的一部分：

Inception相比之前的VGG LeNet这些都是单条线的
Inception 多分支并行 再concat

Inception 第一版GoogleNet 特征总结： NIN Network in Network
Incept_v3: NININ 套了两次

2. ResNet

仅仅是go deeper并不能提升准确率

引入短路连接

实际实现：

残差网络越深 error越低

源码实现：

def conv_block(input_tensor,
               kernel_size,
               filters,
               stage,
               block,
               strides=(2, 2)):
    """A block that has a conv layer at shortcut.

    # Arguments
        input_tensor: input tensor
        kernel_size: default 3, the kernel size of
            middle conv layer at main path
        filters: list of integers, the filters of 3 conv layer at main path
        stage: integer, current stage label, used for generating layer names
        block: 'a','b'..., current block label, used for generating layer names
        strides: Strides for the first conv layer in the block.

    # Returns
        Output tensor for the block.

    Note that from stage 3,
    the first conv layer at main path is with strides=(2, 2)
    And the shortcut should have strides=(2, 2) as well
    """
    filters1, filters2, filters3 = filters
    if backend.image_data_format() == 'channels_last':
        bn_axis = 3
    else:
        bn_axis = 1
    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = layers.Conv2D(filters1, (1, 1), strides=strides,
                      kernel_initializer='he_normal',
                      name=conv_name_base + '2a')(input_tensor)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
    x = layers.Activation('relu')(x)

    x = layers.Conv2D(filters2, kernel_size, padding='same',
                      kernel_initializer='he_normal',
                      name=conv_name_base + '2b')(x)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
    x = layers.Activation('relu')(x)

    x = layers.Conv2D(filters3, (1, 1),
                      kernel_initializer='he_normal',
                      name=conv_name_base + '2c')(x)
    x = layers.BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)

    shortcut = layers.Conv2D(filters3, (1, 1), strides=strides,
                             kernel_initializer='he_normal',
                             name=conv_name_base + '1')(input_tensor)
    shortcut = layers.BatchNormalization(
        axis=bn_axis, name=bn_name_base + '1')(shortcut)

    x = layers.add([x, shortcut])
    x = layers.Activation('relu')(x)

layers.add([x, shortcut])直接是数值上的相加 F(X)+X

3. DenseNet

在一个block里面 卷积计算的feature_map都会累加到最后的输出

VGG ResNet DenceNet比较

4. MobileNet

。。。