GoogLeNet在2014的ImageNet分类任务上击败了VGG-Nets夺得冠军,其实力肯定是非常深厚的,GoogLeNet跟AlexNet,VGG-Nets这种单纯依靠加深网络结构进而改进网络性能的思路不一样,它另辟幽径,在加深网络的同时(22层),也在网络结构上做了创新,引入Inception结构代替了单纯的卷积+激活的传统操作(这思路最早由Network in Network提出)。GoogLeNet进一步把对卷积神经网络的研究推上新的高度。
defConv2d_BN(x, nb_filter,kernel_size, padding='same',strides=(1,1),name=None):if name isnotNone:
bn_name = name +'_bn'
conv_name = name +'_conv'else:
bn_name =None
conv_name =None
x = Conv2D(nb_filter,kernel_size,padding=padding,strides=strides,activation='relu',name=conv_name)(x)
x = BatchNormalization(axis=3,name=bn_name)(x)return x
defInception(x,nb_filter):
branch1x1 = Conv2d_BN(x,nb_filter,(1,1), padding='same',strides=(1,1),name=None)
branch3x3 = Conv2d_BN(x,nb_filter,(1,1), padding='same',strides=(1,1),name=None)
branch3x3 = Conv2d_BN(branch3x3,nb_filter,(3,3), padding='same',strides=(1,1),name=None)
branch5x5 = Conv2d_BN(x,nb_filter,(1,1), padding='same',strides=(1,1),name=None)
branch5x5 = Conv2d_BN(branch5x5,nb_filter,(1,1), padding='same',strides=(1,1),name=None)
branchpool = MaxPooling2D(pool_size=(3,3),strides=(1,1),padding='same')(x)
branchpool = Conv2d_BN(branchpool,nb_filter,(1,1),padding='same',strides=(1,1),name=None)
x = concatenate([branch1x1,branch3x3,branch5x5,branchpool],axis=3)return x
defGoogLeNet():
inpt = Input(shape=(224,224,3))#padding = 'same',填充为(步长-1)/2,还可以用ZeroPadding2D((3,3))
x = Conv2d_BN(inpt,64,(7,7),strides=(2,2),padding='same')
x = MaxPooling2D(pool_size=(3,3),strides=(2,2),padding='same')(x)
x = Conv2d_BN(x,192,(3,3),strides=(1,1),padding='same')
x = MaxPooling2D(pool_size=(3,3),strides=(2,2),padding='same')(x)
x = Inception(x,64)#256
x = Inception(x,120)#480
x = MaxPooling2D(pool_size=(3,3),strides=(2,2),padding='same')(x)
x = Inception(x,128)#512
x = Inception(x,128)
x = Inception(x,128)
x = Inception(x,132)#528
x = Inception(x,208)#832
x = MaxPooling2D(pool_size=(3,3),strides=(2,2),padding='same')(x)
x = Inception(x,208)
x = Inception(x,256)#1024
x = AveragePooling2D(pool_size=(7,7),strides=(7,7),padding='same')(x)
x = Dropout(0.4)(x)
x = Dense(1000,activation='relu')(x)
x = Dense(1000,activation='softmax')(x)
model = Model(inpt,x,name='inception')return model
defConv2d_BN(x, nb_filter,kernel_size, strides=(1,1), padding='same',name=None):if name isnotNone:
bn_name = name +'_bn'
conv_name = name +'_conv'else:
bn_name =None
conv_name =None
x = Conv2D(nb_filter,kernel_size,padding=padding,strides=strides,activation='relu',name=conv_name)(x)
x = BatchNormalization(axis=3,name=bn_name)(x)return x
defConv_Block(inpt,nb_filter,kernel_size,strides=(1,1), with_conv_shortcut=False):
x = Conv2d_BN(inpt,nb_filter=nb_filter[0],kernel_size=(1,1),strides=strides,padding='same')
x = Conv2d_BN(x, nb_filter=nb_filter[1], kernel_size=(3,3), padding='same')
x = Conv2d_BN(x, nb_filter=nb_filter[2], kernel_size=(1,1), padding='same')if with_conv_shortcut:
shortcut = Conv2d_BN(inpt,nb_filter=nb_filter[2],strides=strides,kernel_size=kernel_size)
x = add([x,shortcut])return x
else:
x = add([x,inpt])return x
defResNet50():
inpt = Input(shape=(224,224,3))
x = ZeroPadding2D((3,3))(inpt)
x = Conv2d_BN(x,nb_filter=64,kernel_size=(7,7),strides=(2,2),padding='valid')
x = MaxPooling2D(pool_size=(3,3),strides=(2,2),padding='same')(x)
x = Conv_Block(x,nb_filter=[64,64,256],kernel_size=(3,3),strides=(1,1),with_conv_shortcut=True)
x = Conv_Block(x,nb_filter=[64,64,256],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[64,64,256],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[128,128,512],kernel_size=(3,3),strides=(2,2),with_conv_shortcut=True)
x = Conv_Block(x,nb_filter=[128,128,512],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[128,128,512],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[128,128,512],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[256,256,1024],kernel_size=(3,3),strides=(2,2),with_conv_shortcut=True)
x = Conv_Block(x,nb_filter=[256,256,1024],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[256,256,1024],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[256,256,1024],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[256,256,1024],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[256,256,1024],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[512,512,2048],kernel_size=(3,3),strides=(2,2),with_conv_shortcut=True)
x = Conv_Block(x,nb_filter=[512,512,2048],kernel_size=(3,3))
x = Conv_Block(x,nb_filter=[512,512,2048],kernel_size=(3,3))
x = AveragePooling2D(pool_size=(7,7))(x)
x = Flatten()(x)
x = Dense(1000,activation='softmax')(x)
model = Model(inputs=inpt,outputs=x)return model
defDenseNet121(nb_dense_block=4, growth_rate=32, nb_filter=64, reduction=0.0, dropout_rate=0.0, weight_decay=1e-4, classes=1000, weights_path=None):'''Instantiate the DenseNet 121 architecture,
# Arguments
nb_dense_block: number of dense blocks to add to end
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters
reduction: reduction factor of transition blocks.
dropout_rate: dropout rate
weight_decay: weight decay factor
classes: optional number of classes to classify images
weights_path: path to pre-trained weights
# Returns
A Keras model instance.
'''
eps =1.1e-5# compute compression factor
compression =1.0- reduction
# Handle Dimension Ordering for different backendsglobal concat_axis
if K.image_dim_ordering()=='tf':
concat_axis =3
img_input = Input(shape=(224,224,3), name='data')else:
concat_axis =1
img_input = Input(shape=(3,224,224), name='data')# From architecture for ImageNet (Table 1 in the paper)
nb_filter =64
nb_layers =[6,12,24,16]# For DenseNet-121# Initial convolution
x = ZeroPadding2D((3,3), name='conv1_zeropadding')(img_input)
x = Convolution2D(nb_filter,7,7, subsample=(2,2), name='conv1', bias=False)(x)
x = BatchNormalization(epsilon=eps, axis=concat_axis, name='conv1_bn')(x)
x = Scale(axis=concat_axis, name='conv1_scale')(x)
x = Activation('relu', name='relu1')(x)
x = ZeroPadding2D((1,1), name='pool1_zeropadding')(x)
x = MaxPooling2D((3,3), strides=(2,2), name='pool1')(x)# Add dense blocksfor block_idx inrange(nb_dense_block -1):
stage = block_idx+2
x, nb_filter = dense_block(x, stage, nb_layers[block_idx], nb_filter, growth_rate, dropout_rate=dropout_rate, weight_decay=weight_decay)# Add transition_block
x = transition_block(x, stage, nb_filter, compression=compression, dropout_rate=dropout_rate, weight_decay=weight_decay)
nb_filter =int(nb_filter * compression)
final_stage = stage +1
x, nb_filter = dense_block(x, final_stage, nb_layers[-1], nb_filter, growth_rate, dropout_rate=dropout_rate, weight_decay=weight_decay)
x = BatchNormalization(epsilon=eps, axis=concat_axis, name='conv'+str(final_stage)+'_blk_bn')(x)
x = Scale(axis=concat_axis, name='conv'+str(final_stage)+'_blk_scale')(x)
x = Activation('relu', name='relu'+str(final_stage)+'_blk')(x)
x = GlobalAveragePooling2D(name='pool'+str(final_stage))(x)
x = Dense(classes, name='fc6')(x)
x = Activation('softmax', name='prob')(x)
model = Model(img_input, x, name='densenet')if weights_path isnotNone:
model.load_weights(weights_path)return model
defconv_block(x, stage, branch, nb_filter, dropout_rate=None, weight_decay=1e-4):'''Apply BatchNorm, Relu, bottleneck 1x1 Conv2D, 3x3 Conv2D, and option dropout
# Arguments
x: input tensor
stage: index for dense block
branch: layer index within each dense block
nb_filter: number of filters
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps =1.1e-5
conv_name_base ='conv'+str(stage)+'_'+str(branch)
relu_name_base ='relu'+str(stage)+'_'+str(branch)# 1x1 Convolution (Bottleneck layer)
inter_channel = nb_filter *4
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x1_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x1_scale')(x)
x = Activation('relu', name=relu_name_base+'_x1')(x)
x = Convolution2D(inter_channel,1,1, name=conv_name_base+'_x1', bias=False)(x)if dropout_rate:
x = Dropout(dropout_rate)(x)# 3x3 Convolution
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_x2_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_x2_scale')(x)
x = Activation('relu', name=relu_name_base+'_x2')(x)
x = ZeroPadding2D((1,1), name=conv_name_base+'_x2_zeropadding')(x)
x = Convolution2D(nb_filter,3,3, name=conv_name_base+'_x2', bias=False)(x)if dropout_rate:
x = Dropout(dropout_rate)(x)return x
deftransition_block(x, stage, nb_filter, compression=1.0, dropout_rate=None, weight_decay=1E-4):''' Apply BatchNorm, 1x1 Convolution, averagePooling, optional compression, dropout
# Arguments
x: input tensor
stage: index for dense block
nb_filter: number of filters
compression: calculated as 1 - reduction. Reduces the number of feature maps in the transition block.
dropout_rate: dropout rate
weight_decay: weight decay factor
'''
eps =1.1e-5
conv_name_base ='conv'+str(stage)+'_blk'
relu_name_base ='relu'+str(stage)+'_blk'
pool_name_base ='pool'+str(stage)
x = BatchNormalization(epsilon=eps, axis=concat_axis, name=conv_name_base+'_bn')(x)
x = Scale(axis=concat_axis, name=conv_name_base+'_scale')(x)
x = Activation('relu', name=relu_name_base)(x)
x = Convolution2D(int(nb_filter * compression),1,1, name=conv_name_base, bias=False)(x)if dropout_rate:
x = Dropout(dropout_rate)(x)
x = AveragePooling2D((2,2), strides=(2,2), name=pool_name_base)(x)return x
defdense_block(x, stage, nb_layers, nb_filter, growth_rate, dropout_rate=None, weight_decay=1e-4, grow_nb_filters=True):''' Build a dense_block where the output of each conv_block is fed to subsequent ones
# Arguments
x: input tensor
stage: index for dense block
nb_layers: the number of layers of conv_block to append to the model.
nb_filter: number of filters
growth_rate: growth rate
dropout_rate: dropout rate
weight_decay: weight decay factor
grow_nb_filters: flag to decide to allow number of filters to grow
'''
eps =1.1e-5
concat_feat = x
for i inrange(nb_layers):
branch = i+1
x = conv_block(concat_feat, stage, branch, growth_rate, dropout_rate, weight_decay)
concat_feat = merge([concat_feat, x], mode='concat', concat_axis=concat_axis, name='concat_'+str(stage)+'_'+str(branch))if grow_nb_filters:
nb_filter += growth_rate
return concat_feat, nb_filter