神经网络学习小记录46——Densenet模型的复现详解

梦里梦外; 2023-07-24 14:44 148阅读 0赞

### 神经网络学习小记录46——Densenet模型的复现详解 ###

*  学习前言
 *  什么是Densenet
 *  代码下载
 *  Densenet
 *   *  1、Densenet的整体结构
     *  2、DenseBlock
     *  3、Transition Layer
 *  网络实现代码

# 学习前言 #

据说Densenet比Resnet还要厉害，我决定好好学一下。  
![在这里插入图片描述][20190723165901974.jpg_pic_center]

# 什么是Densenet #

ResNet模型的出现使得深度学习神经网络可以变得更深，进而实现了更高的准确度。ResNet模型的核心是通过建立前面层与后面层之间的短路连接（shortcuts），这有助于训练过程中梯度的反向传播，从而能训练出更深的CNN网络。

DenseNet模型，它的基本思路与ResNet一致，也是建立前面层与后面层的短路连接，不同的是，但是它建立的是前面所有层与后面层的密集连接。

DenseNet还有一个特点是实现了特征重用。

这些特点让DenseNet在参数和计算成本更少的情形下实现比ResNet更优的性能。

DenseNet示意图如下：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NDc5MTk2NA_size_16_color_FFFFFF_t_70_pic_center]

# 代码下载 #

[https://github.com/bubbliiiing/classic-convolution-network][https_github.com_bubbliiiing_classic-convolution-network]

# Densenet #

## 1、Densenet的整体结构 ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NDc5MTk2NA_size_16_color_FFFFFF_t_70_pic_center]  
如图所示Densenet由**DenseBlock**和**中间的间隔模块Transition Layer**组成。  
1、DenseBlock：DenseBlock指的就是DenseNet特有的模块，如下图所示，前面所有层与后面层的具有密集连接，**在同一个DenseBlock当中，特征层的高宽不会发生改变，但是通道数会发生改变。**  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NDc5MTk2NA_size_16_color_FFFFFF_t_70_pic_center 1]  
2、Transition Layer：Transition Layer是将不同**DenseBlock之间进行连接的模块，主要功能是整合上一个DenseBlock获得的特征**，并且缩小上一个DenseBlock的宽高，**在Transition Layer中，一般会使用一个步长为2的AveragePooling2D缩小特征层的宽高。**

## 2、DenseBlock ##

DenseBlock的实现示意图如图所示：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NDc5MTk2NA_size_16_color_FFFFFF_t_70_pic_center 2]  
以前获得的特征会在保留后不断的堆叠起来。

以一个简单例子来表现一下具体的DenseBlock的流程：  
**假设输入特征层为X0**。  
1、对x0进行一次**1x1卷积**调整**通道数到4\*32**后，再利用**3x3卷积**获得一个**32通道的特征层**，此时会获得**一个shape为(h,w,32)的特征层x1**。  
2、将**获得的x1和初始的x0堆叠**，获得一个新的特征层，这个特征层会**同时保留初始x0的特征**也会**保留经过卷积处理后的特征**。  
3、反复经过步骤1、2的处理，**原始的特征会一直得到保留，经过卷积处理后的特征也会得到保留。当网络程度不断加深，就可以实现前面所有层与后面层的具有密集连接。**  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NDc5MTk2NA_size_16_color_FFFFFF_t_70_pic_center 1]  
实现代码为：

def dense_block(x, blocks, name):
        for i in range(blocks):
            x = conv_block(x, 32, name=name + '_block' + str(i + 1))
        return x
    def conv_block(x, growth_rate, name):
        bn_axis = 3 
        x1 = layers.BatchNormalization(axis=bn_axis,
                                       epsilon=1.001e-5,
                                       name=name + '_0_bn')(x)
        x1 = layers.Activation('relu', name=name + '_0_relu')(x1)
        x1 = layers.Conv2D(4 * growth_rate, 1,
                           use_bias=False,
                           name=name + '_1_conv')(x1)
        x1 = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,
                                       name=name + '_1_bn')(x1)
        x1 = layers.Activation('relu', name=name + '_1_relu')(x1)
        x1 = layers.Conv2D(growth_rate, 3,
                           padding='same',
                           use_bias=False,
                           name=name + '_2_conv')(x1)
        x = layers.Concatenate(axis=bn_axis, name=name + '_concat')([x, x1])
        return x

## 3、Transition Layer ##

Transition Layer将不同**DenseBlock之间进行连接的模块，主要功能是整合上一个DenseBlock获得的特征**，并且缩小上一个DenseBlock的宽高，**在Transition Layer中，一般会使用一个步长为2的AveragePooling2D缩小特征层的宽高。**  
实现代码为：

def transition_block(x, reduction, name):
        bn_axis = 3
        x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,
                                      name=name + '_bn')(x)
        x = layers.Activation('relu', name=name + '_relu')(x)
        x = layers.Conv2D(int(backend.int_shape(x)[bn_axis] * reduction), 1,
                          use_bias=False,
                          name=name + '_conv')(x)
        x = layers.AveragePooling2D(2, strides=2, name=name + '_pool')(x)
        return x

# 网络实现代码 #

from keras.preprocessing import image
    
    from keras.models import Model
    from keras import layers
    from keras.applications import imagenet_utils
    from keras.applications.imagenet_utils import decode_predictions
    from keras.utils.data_utils import get_file
    from keras import backend 
    import numpy as np
    
    BASE_WEIGTHS_PATH = (
        'https://github.com/keras-team/keras-applications/'
        'releases/download/densenet/')
    DENSENET121_WEIGHT_PATH = (
        BASE_WEIGTHS_PATH +
        'densenet121_weights_tf_dim_ordering_tf_kernels.h5')
    DENSENET169_WEIGHT_PATH = (
        BASE_WEIGTHS_PATH +
        'densenet169_weights_tf_dim_ordering_tf_kernels.h5')
    DENSENET201_WEIGHT_PATH = (
        BASE_WEIGTHS_PATH +
        'densenet201_weights_tf_dim_ordering_tf_kernels.h5')
    
    def dense_block(x, blocks, name):
        for i in range(blocks):
            x = conv_block(x, 32, name=name + '_block' + str(i + 1))
        return x
    def conv_block(x, growth_rate, name):
        bn_axis = 3 
        x1 = layers.BatchNormalization(axis=bn_axis,
                                       epsilon=1.001e-5,
                                       name=name + '_0_bn')(x)
        x1 = layers.Activation('relu', name=name + '_0_relu')(x1)
        x1 = layers.Conv2D(4 * growth_rate, 1,
                           use_bias=False,
                           name=name + '_1_conv')(x1)
        x1 = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,
                                       name=name + '_1_bn')(x1)
        x1 = layers.Activation('relu', name=name + '_1_relu')(x1)
        x1 = layers.Conv2D(growth_rate, 3,
                           padding='same',
                           use_bias=False,
                           name=name + '_2_conv')(x1)
        x = layers.Concatenate(axis=bn_axis, name=name + '_concat')([x, x1])
        return x
    
    
    def transition_block(x, reduction, name):
        bn_axis = 3
        x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,
                                      name=name + '_bn')(x)
        x = layers.Activation('relu', name=name + '_relu')(x)
        x = layers.Conv2D(int(backend.int_shape(x)[bn_axis] * reduction), 1,
                          use_bias=False,
                          name=name + '_conv')(x)
        x = layers.AveragePooling2D(2, strides=2, name=name + '_pool')(x)
        return x
    
    
    
    
    def DenseNet(blocks,
                 input_shape=None,
                 classes=1000,
                 **kwargs):
    
    
        img_input = layers.Input(shape=input_shape)
    
        bn_axis = 3
    
        # 224,224,3 -> 112,112,64
        x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input)
        x = layers.Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
        x = layers.BatchNormalization(
            axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x)
        x = layers.Activation('relu', name='conv1/relu')(x)
        
        # 112,112,64 -> 56,56,64
        x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)))(x)
        x = layers.MaxPooling2D(3, strides=2, name='pool1')(x)
    
        # 56,56,64 -> 56,56,64+32*block[0]
        # Densenet121 56,56,64 -> 56,56,64+32*6 == 56,56,256
        x = dense_block(x, blocks[0], name='conv2')
    
        # 56,56,64+32*block[0] -> 28,28,32+16*block[0]
        # Densenet121 56,56,256 -> 28,28,32+16*6 == 28,28,128
        x = transition_block(x, 0.5, name='pool2')
    
        # 28,28,32+16*block[0] -> 28,28,32+16*block[0]+32*block[1]
        # Densenet121 28,28,128 -> 28,28,128+32*12 == 28,28,512
        x = dense_block(x, blocks[1], name='conv3')
        
        # Densenet121 28,28,512 -> 14,14,256
        x = transition_block(x, 0.5, name='pool3')
    
        # Densenet121 14,14,256 -> 14,14,256+32*block[2] == 14,14,1024
        x = dense_block(x, blocks[2], name='conv4')
    
        # Densenet121 14,14,1024 -> 7,7,512
        x = transition_block(x, 0.5, name='pool4')
    
        # Densenet121 7,7,512 -> 7,7,256+32*block[3] == 7,7,1024
        x = dense_block(x, blocks[3], name='conv5')
    
        x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x)
        x = layers.Activation('relu', name='relu')(x)
    
        x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
        x = layers.Dense(classes, activation='softmax', name='fc1000')(x)
    
        inputs = img_input
    
        if blocks == [6, 12, 24, 16]:
            model = Model(inputs, x, name='densenet121')
        elif blocks == [6, 12, 32, 32]:
            model = Model(inputs, x, name='densenet169')
        elif blocks == [6, 12, 48, 32]:
            model = Model(inputs, x, name='densenet201')
        else:
            model = Model(inputs, x, name='densenet')
        return model
    
    
    def DenseNet121(input_shape=[224,224,3],
                    classes=1000,
                    **kwargs):
        return DenseNet([6, 12, 24, 16],
                        input_shape, classes,
                        **kwargs)
    
    
    def DenseNet169(input_shape=[224,224,3],
                    classes=1000,
                    **kwargs):
        return DenseNet([6, 12, 32, 32],
                        input_shape, classes,
                        **kwargs)
    
    
    def DenseNet201(input_shape=[224,224,3],
                    classes=1000,
                    **kwargs):
        return DenseNet([6, 12, 48, 32],
                        input_shape, classes,
                        **kwargs)
    
    def preprocess_input(x):
        x /= 255.
        mean = [0.485, 0.456, 0.406]
        std = [0.229, 0.224, 0.225]
        x[..., 0] -= mean[0]
        x[..., 1] -= mean[1]
        x[..., 2] -= mean[2]
        if std is not None:
            x[..., 0] /= std[0]
            x[..., 1] /= std[1]
            x[..., 2] /= std[2]
        return x
    
    
    if __name__ == '__main__':
        # model = DenseNet121()
        # weights_path = get_file(
        # 'densenet121_weights_tf_dim_ordering_tf_kernels.h5',
        # DENSENET121_WEIGHT_PATH,
        # cache_subdir='models',
        # file_hash='9d60b8095a5708f2dcce2bca79d332c7')
        
        model = DenseNet169()
        weights_path = get_file(
        'densenet169_weights_tf_dim_ordering_tf_kernels.h5',
        DENSENET169_WEIGHT_PATH,
        cache_subdir='models',
        file_hash='d699b8f76981ab1b30698df4c175e90b')
        
        # model = DenseNet201()
        # weights_path = get_file(
        # 'densenet201_weights_tf_dim_ordering_tf_kernels.h5',
        # DENSENET201_WEIGHT_PATH,
        # cache_subdir='models',
        # file_hash='1ceb130c1ea1b78c3bf6114dbdfd8807')
        model.load_weights(weights_path)
        model.summary()
        img_path = 'elephant.jpg'
        img = image.load_img(img_path, target_size=(224, 224))
        x = image.img_to_array(img)
        x = np.expand_dims(x, axis=0)
        x = preprocess_input(x)
        print('Input image shape:', x.shape)
    
        preds = model.predict(x)
        print(np.argmax(preds))
        print('Predicted:', decode_predictions(preds))

[20190723165901974.jpg_pic_center]: /images/20230528/ec61e04e91f34307a698885f23900fcd.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NDc5MTk2NA_size_16_color_FFFFFF_t_70_pic_center]: /images/20230528/e126ad02936049418926e08b33967d6f.png
[https_github.com_bubbliiiing_classic-convolution-network]: https://github.com/bubbliiiing/classic-convolution-network
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NDc5MTk2NA_size_16_color_FFFFFF_t_70_pic_center 1]: /images/20230528/14bdc11ce759467eab10d489d085f9a8.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80NDc5MTk2NA_size_16_color_FFFFFF_t_70_pic_center 2]: /images/20230528/cd0a894cbcc6404892533b1498228a5c.png