mobileNetV3介绍

mobileNet系统主要针对在手机上运能运行高性能低资源的网络。而mobileNetv3主要利用网络架构搜索（NAS），搜索出来的一种算法。它比v2版本的精度提高了ImageNet分类上提高了6%。
mobilev3主要由如下优点：
1.大量使用11和33的卷积代替55的卷积，减少了参数量。在v2中先使用33的卷积在使用11的卷积，而在v3中则先11在使用3*3。论文里说这样使用是保留了高维特征空间，减少了反向传播的延迟
2.引入残差块和轻量级的注意力机制，轻量级注意力模块
并激发成瓶颈结构，更好的提取特征。

3、采用了h-swish计算速度更快，在移动设备中提高了网络的准确性。

网络复现实现代码 mobilenetV3 large

from keras.layers import Conv2D, DepthwiseConv2D, Dense, GlobalAveragePooling2D,Input
from keras.layers import Activation, BatchNormalization, Add, Multiply, Reshape
from keras.models import Model
from keras import backend as K

alpha = 1
def relu6(x): # relu函数 return K.relu(x, max_value=6.0)

def hard_swish(x): # 利用relu函数乘上x模拟sigmoid return x * K.relu(x + 3.0, max_value=6.0) / 6.0

def return_activation(x, nl): # 用于判断使用哪个激活函数 if nl == 'HS': x = Activation(hard_swish)(x) if nl == 'RE': x = Activation(relu6)(x) return x

def conv_block(inputs, filters, kernel, strides, nl): # 一个卷积单元，也就是conv2d + batchnormalization + activation channel_axis = 1 if K.image_data_format() == 'channels_first' else -1 x = Conv2D(filters, kernel, padding='same', strides=strides)(inputs) x = BatchNormalization(axis=channel_axis)(x) return return_activation(x, nl)

def squeeze(inputs): # 注意力机制单元 input_channels = int(inputs.shape[-1]) x = GlobalAveragePooling2D()(inputs) x = Dense(int(input_channels/4))(x) x = Activation(relu6)(x) x = Dense(input_channels)(x) x = Activation(hard_swish)(x) x = Reshape((1, 1, input_channels))(x) x = Multiply()([inputs, x]) return x

def bottleneck(inputs, filters, kernel, up_dim, stride, sq, nl): channel_axis = 1 if K.image_data_format() == 'channels_first' else -1 input_shape = K.int_shape(inputs) tchannel = int(up_dim) cchannel = int(alpha * filters) r = stride == 1 and input_shape[3] == filters # 1x1卷积调整通道数，通道数上升 x = conv_block(inputs, tchannel, (1, 1), (1, 1), nl) # 进行3x3深度可分离卷积 x = DepthwiseConv2D(kernel, strides=(stride, stride), depth_multiplier=1, padding='same')(x) x = BatchNormalization(axis=channel_axis)(x) x = return_activation(x, nl) # 引入注意力机制 if sq: x = squeeze(x) # 下降通道数 x = Conv2D(cchannel, (1, 1), strides=(1, 1), padding='same')(x) x = BatchNormalization(axis=channel_axis)(x) if r: x = Add()([x, inputs]) return x

def MobileNetv3_large(shape = (224,224,3),n_class = 1000): inputs = Input(shape) # 224,224,3 -> 112,112,16 x = conv_block(inputs, 16, (3, 3), strides=(2, 2), nl='HS') x = bottleneck(x, 16, (3, 3), up_dim=16, stride=1, sq=False, nl='RE') # 112,112,16 -> 56,56,24 x = bottleneck(x, 24, (3, 3), up_dim=64, stride=2, sq=False, nl='RE') x = bottleneck(x, 24, (3, 3), up_dim=72, stride=1, sq=False, nl='RE') # 56,56,24 -> 28,28,40 x = bottleneck(x, 40, (5, 5), up_dim=72, stride=2, sq=True, nl='RE') x = bottleneck(x, 40, (5, 5), up_dim=120, stride=1, sq=True, nl='RE') x = bottleneck(x, 40, (5, 5), up_dim=120, stride=1, sq=True, nl='RE') # 28,28,40 -> 14,14,80 x = bottleneck(x, 80, (3, 3), up_dim=240, stride=2, sq=False, nl='HS') x = bottleneck(x, 80, (3, 3), up_dim=200, stride=1, sq=False, nl='HS') x = bottleneck(x, 80, (3, 3), up_dim=184, stride=1, sq=False, nl='HS') x = bottleneck(x, 80, (3, 3), up_dim=184, stride=1, sq=False, nl='HS') # 14,14,80 -> 14,14,112 x = bottleneck(x, 112, (3, 3), up_dim=480, stride=1, sq=True, nl='HS') x = bottleneck(x, 112, (3, 3), up_dim=672, stride=1, sq=True, nl='HS') # 14,14,112 -> 7,7,160 x = bottleneck(x, 160, (5, 5), up_dim=672, stride=2, sq=True, nl='HS') x = bottleneck(x, 160, (5, 5), up_dim=960, stride=1, sq=True, nl='HS') x = bottleneck(x, 160, (5, 5), up_dim=960, stride=1, sq=True, nl='HS') # 7,7,160 -> 7,7,960 x = conv_block(x, 960, (1, 1), strides=(1, 1), nl='HS') x = GlobalAveragePooling2D()(x) x = Reshape((1, 1, 960))(x) x = Conv2D(1280, (1, 1), padding='same')(x) x = return_activation(x, 'HS') x = Conv2D(n_class, (1, 1), padding='same', activation='softmax')(x) x = Reshape((n_class,))(x) model = Model(inputs, x) return model
if __name__ == "__main__": model = MobileNetv3_large() model.summary()


  

 

• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• 51
• 52
• 53
• 54
• 55
• 56
• 57
• 58
• 59
• 60
• 61
• 62
• 63
• 64
• 65
• 66
• 67
• 68
• 69
• 70
• 71
• 72
• 73
• 74
• 75
• 76
• 77
• 78
• 79
• 80
• 81
• 82
• 83
• 84
• 85
• 86
• 87
• 88
• 89
• 90
• 91
• 92
• 93
• 94
• 95
• 96
• 97
• 98
• 99
• 100
• 101
• 102
• 103
• 104
• 105
• 106
• 107
• 108
• 109
• 110
• 111
• 112
• 113
• 114
• 115
• 116
• 117
• 118
• 119
• 120
• 121

网络复现实现代码 mobilenetV3 small

small主要减少了通道数，降低了参数量

from keras.layers import Conv2D, DepthwiseConv2D, Dense, GlobalAveragePooling2D,Input
from keras.layers import Activation, BatchNormalization, Add, Multiply, Reshape
from keras.models import Model
from keras import backend as K

alpha = 1
def relu6(x): # relu函数 return K.relu(x, max_value=6.0)

def hard_swish(x): # 利用relu函数乘上x模拟sigmoid return x * K.relu(x + 3.0, max_value=6.0) / 6.0

def return_activation(x, nl): # 用于判断使用哪个激活函数 if nl == 'HS': x = Activation(hard_swish)(x) if nl == 'RE': x = Activation(relu6)(x) return x

def conv_block(inputs, filters, kernel, strides, nl): # 一个卷积单元，也就是conv2d + batchnormalization + activation channel_axis = 1 if K.image_data_format() == 'channels_first' else -1 x = Conv2D(filters, kernel, padding='same', strides=strides)(inputs) x = BatchNormalization(axis=channel_axis)(x) return return_activation(x, nl)

def squeeze(inputs): # 注意力机制单元 input_channels = int(inputs.shape[-1]) x = GlobalAveragePooling2D()(inputs) x = Dense(int(input_channels/4))(x) x = Activation(relu6)(x) x = Dense(input_channels)(x) x = Activation(hard_swish)(x) x = Reshape((1, 1, input_channels))(x) x = Multiply()([inputs, x]) return x

def bottleneck(inputs, filters, kernel, up_dim, stride, sq, nl): channel_axis = 1 if K.image_data_format() == 'channels_first' else -1 input_shape = K.int_shape(inputs) tchannel = int(up_dim) cchannel = int(alpha * filters) r = stride == 1 and input_shape[3] == filters # 1x1卷积调整通道数，通道数上升 x = conv_block(inputs, tchannel, (1, 1), (1, 1), nl) # 进行3x3深度可分离卷积 x = DepthwiseConv2D(kernel, strides=(stride, stride), depth_multiplier=1, padding='same')(x) x = BatchNormalization(axis=channel_axis)(x) x = return_activation(x, nl) # 引入注意力机制 if sq: x = squeeze(x) # 下降通道数 x = Conv2D(cchannel, (1, 1), strides=(1, 1), padding='same')(x) x = BatchNormalization(axis=channel_axis)(x) if r: x = Add()([x, inputs]) return x

def MobileNetv3_small(shape = (224,224,3),n_class = 1000): inputs = Input(shape) # 224,224,3 -> 112,112,16 x = conv_block(inputs, 16, (3, 3), strides=(2, 2), nl='HS') # 112,112,16 -> 56,56,16 x = bottleneck(x, 16, (3, 3), up_dim=16, stride=2, sq=True, nl='RE') # 56,56,16 -> 28,28,24 x = bottleneck(x, 24, (3, 3), up_dim=72, stride=2, sq=False, nl='RE') x = bottleneck(x, 24, (3, 3), up_dim=88, stride=1, sq=False, nl='RE') # 28,28,24 -> 14,14,40 x = bottleneck(x, 40, (5, 5), up_dim=96, stride=2, sq=True, nl='HS') x = bottleneck(x, 40, (5, 5), up_dim=240, stride=1, sq=True, nl='HS') x = bottleneck(x, 40, (5, 5), up_dim=240, stride=1, sq=True, nl='HS') # 14,14,40 -> 14,14,48 x = bottleneck(x, 48, (5, 5), up_dim=120, stride=1, sq=True, nl='HS') x = bottleneck(x, 48, (5, 5), up_dim=144, stride=1, sq=True, nl='HS') # 14,14,48 -> 7,7,96 x = bottleneck(x, 96, (5, 5), up_dim=288, stride=2, sq=True, nl='HS') x = bottleneck(x, 96, (5, 5), up_dim=576, stride=1, sq=True, nl='HS') x = bottleneck(x, 96, (5, 5), up_dim=576, stride=1, sq=True, nl='HS') x = conv_block(x, 576, (1, 1), strides=(1, 1), nl='HS') x = GlobalAveragePooling2D()(x) x = Reshape((1, 1, 576))(x) x = Conv2D(1024, (1, 1), padding='same')(x) x = return_activation(x, 'HS') x = Conv2D(n_class, (1, 1), padding='same', activation='softmax')(x) x = Reshape((n_class,))(x) model = Model(inputs, x) return model
if __name__ == "__main__": model = MobileNetv3_small() model.summary()


  

 

• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• 51
• 52
• 53
• 54
• 55
• 56
• 57
• 58
• 59
• 60
• 61
• 62
• 63
• 64
• 65
• 66
• 67
• 68
• 69
• 70
• 71
• 72
• 73
• 74
• 75
• 76
• 77
• 78
• 79
• 80
• 81
• 82
• 83
• 84
• 85
• 86
• 87
• 88
• 89
• 90
• 91
• 92
• 93
• 94
• 95
• 96
• 97
• 98
• 99
• 100
• 101
• 102
• 103
• 104
• 105
• 106
• 107
• 108
• 109
• 110
• 111
• 112
• 113
• 114
• 115
• 116
• 117

文章来源: blog.csdn.net，作者：快了的程序猿小可哥，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/qq_35914625/article/details/108015789