keras, TensorFlow中加入注意力机制

第一步：找到要修改文件的源代码

在里面添加通道注意力机制和空间注意力机制

所需库

from keras.layers import GlobalAveragePooling2D, GlobalMaxPooling2D, Reshape, Dense, multiply, Permute, Concatenate, Conv2D, Add, Activation, Lambda
from keras import backend as K
from keras.activations import sigmoid

通道注意力机制

def channel_attention(input_feature, ratio=8):
	
	channel_axis = 1 if K.image_data_format() == "channels_first" else -1
	channel = input_feature._keras_shape[channel_axis]
	
	shared_layer_one = Dense(channel//ratio,
							 kernel_initializer='he_normal',
							 activation = 'relu',
							 use_bias=True,
							 bias_initializer='zeros')

	shared_layer_two = Dense(channel,
							 kernel_initializer='he_normal',
							 use_bias=True,
							 bias_initializer='zeros')
	
	avg_pool = GlobalAveragePooling2D()(input_feature)    
	avg_pool = Reshape((1,1,channel))(avg_pool)
	assert avg_pool._keras_shape[1:] == (1,1,channel)
	avg_pool = shared_layer_one(avg_pool)
	assert avg_pool._keras_shape[1:] == (1,1,channel//ratio)
	avg_pool = shared_layer_two(avg_pool)
	assert avg_pool._keras_shape[1:] == (1,1,channel)
	
	max_pool = GlobalMaxPooling2D()(input_feature)
	max_pool = Reshape((1,1,channel))(max_pool)
	assert max_pool._keras_shape[1:] == (1,1,channel)
	max_pool = shared_layer_one(max_pool)
	assert max_pool._keras_shape[1:] == (1,1,channel//ratio)
	max_pool = shared_layer_two(max_pool)
	assert max_pool._keras_shape[1:] == (1,1,channel)
	
	cbam_feature = Add()([avg_pool,max_pool])
	cbam_feature = Activation('hard_sigmoid')(cbam_feature)
	
	if K.image_data_format() == "channels_first":
		cbam_feature = Permute((3, 1, 2))(cbam_feature)
	
	return multiply([input_feature, cbam_feature])

空间注意力机制

def spatial_attention(input_feature):
	kernel_size = 7
	
	if K.image_data_format() == "channels_first":
		channel = input_feature._keras_shape[1]
		cbam_feature = Permute((2,3,1))(input_feature)
	else:
		channel = input_feature._keras_shape[-1]
		cbam_feature = input_feature
	
	avg_pool = Lambda(lambda x: K.mean(x, axis=3, keepdims=True))(cbam_feature)
	assert avg_pool._keras_shape[-1] == 1
	max_pool = Lambda(lambda x: K.max(x, axis=3, keepdims=True))(cbam_feature)
	assert max_pool._keras_shape[-1] == 1
	concat = Concatenate(axis=3)([avg_pool, max_pool])
	assert concat._keras_shape[-1] == 2
	cbam_feature = Conv2D(filters = 1,
					kernel_size=kernel_size,
					activation = 'hard_sigmoid',
					strides=1,
					padding='same',
					kernel_initializer='he_normal',
					use_bias=False)(concat)
	assert cbam_feature._keras_shape[-1] == 1
	
	if K.image_data_format() == "channels_first":
		cbam_feature = Permute((3, 1, 2))(cbam_feature)
		
	return multiply([input_feature, cbam_feature])

构建CBAM

def cbam_block(cbam_feature,ratio=8):
	"""Contains the implementation of Convolutional Block Attention Module(CBAM) block.
	As described in https://arxiv.org/abs/1807.06521.
	"""
	
	cbam_feature = channel_attention(cbam_feature, ratio)
	cbam_feature = spatial_attention(cbam_feature, )
	return cbam_feature

在相应的位置添加CBAM

  inputs = x
  residual = layers.Conv2D(filter, kernel_size = (1, 1), strides = strides, padding = 'same')(inputs)
  residual = layers.BatchNormalization(axis = bn_axis)(residual)
  cbam = cbam_block(residual)
  x = layers.add([x, residual, cbam])
	

这样就在任意位置加入了注意力机制啦。