# 卷积中的attention map理解及可视化

18 篇文章 0 订阅
引用
Woo S , Park J , Lee J Y , et al. CBAM: Convolutional Block Attention Module[J]. 2018.

https://arxiv.org/pdf/1807.06521.pdf

https://www.jianshu.com/p/4fac94eaca91
https://blog.csdn.net/weixin_36541072/article/details/79126225

### 主要思想

CBAM的结构图

Channel attention module

feature map 的每个channel都被视为一个feature detector，channel attention主要关注于输入图片中什么(what)是有意义的。为了高效地计算channel attention，论文使用最大池化平均池化对feature map在空间维度上进行压缩，得到两个不同的空间背景描述：。使用由MLP组成的共享网络对这两个不同的空间背景描述进行计算得到channel attention map：。计算过程如下：

Spatial attention module.

（上）channel attention module；（下）spatial attention module

"""
@Time   : 2018/10/19
@Author : Li YongHong
@Email  : lyh_robert@163.com
@File   : test.py
"""
import tensorflow as tf
import numpy as np

slim = tf.contrib.slim

def combined_static_and_dynamic_shape(tensor):
"""Returns a list containing static and dynamic values for the dimensions.

Returns a list of static and dynamic values for shape dimensions. This is
useful to preserve static shapes when available in reshape operation.

Args:
tensor: A tensor of any type.

Returns:
A list of size tensor.shape.ndims containing integers or a scalar tensor.
"""
static_tensor_shape = tensor.shape.as_list()
dynamic_tensor_shape = tf.shape(tensor)
combined_shape = []
for index, dim in enumerate(static_tensor_shape):
if dim is not None:
combined_shape.append(dim)
else:
combined_shape.append(dynamic_tensor_shape[index])
return combined_shape

def convolutional_block_attention_module(feature_map, index, inner_units_ratio=0.5):
"""
CBAM: convolution block attention module, which is described in "CBAM: Convolutional Block Attention Module"
Architecture : "https://arxiv.org/pdf/1807.06521.pdf"
If you want to use this module, just plug this module into your network
:param feature_map : input feature map
:param index : the index of convolution block attention module
:param inner_units_ratio: output units number of fully connected layer: inner_units_ratio*feature_map_channel
:return:feature map with channel and spatial attention
"""
with tf.variable_scope("cbam_%s" % (index)):
feature_map_shape = combined_static_and_dynamic_shape(feature_map)
# channel attention
channel_avg_weights = tf.nn.avg_pool(
value=feature_map,
ksize=[1, feature_map_shape[1], feature_map_shape[2], 1],
strides=[1, 1, 1, 1],
)
channel_max_weights = tf.nn.max_pool(
value=feature_map,
ksize=[1, feature_map_shape[1], feature_map_shape[2], 1],
strides=[1, 1, 1, 1],
)
channel_avg_reshape = tf.reshape(channel_avg_weights,
[feature_map_shape[0], 1, feature_map_shape[3]])
channel_max_reshape = tf.reshape(channel_max_weights,
[feature_map_shape[0], 1, feature_map_shape[3]])
channel_w_reshape = tf.concat([channel_avg_reshape, channel_max_reshape], axis=1)

fc_1 = tf.layers.dense(
inputs=channel_w_reshape,
units=feature_map_shape[3] * inner_units_ratio,
name="fc_1",
activation=tf.nn.relu
)
fc_2 = tf.layers.dense(
inputs=fc_1,
units=feature_map_shape[3],
name="fc_2",
activation=None
)
channel_attention = tf.reduce_sum(fc_2, axis=1, name="channel_attention_sum")
channel_attention = tf.nn.sigmoid(channel_attention, name="channel_attention_sum_sigmoid")
channel_attention = tf.reshape(channel_attention, shape=[feature_map_shape[0], 1, 1, feature_map_shape[3]])
feature_map_with_channel_attention = tf.multiply(feature_map, channel_attention)
# spatial attention
channel_wise_avg_pooling = tf.reduce_mean(feature_map_with_channel_attention, axis=3)
channel_wise_max_pooling = tf.reduce_max(feature_map_with_channel_attention, axis=3)

channel_wise_avg_pooling = tf.reshape(channel_wise_avg_pooling,
shape=[feature_map_shape[0], feature_map_shape[1], feature_map_shape[2],
1])
channel_wise_max_pooling = tf.reshape(channel_wise_max_pooling,
shape=[feature_map_shape[0], feature_map_shape[1], feature_map_shape[2],
1])

channel_wise_pooling = tf.concat([channel_wise_avg_pooling, channel_wise_max_pooling], axis=3)
spatial_attention = slim.conv2d(
channel_wise_pooling,
1,
[7, 7],
activation_fn=tf.nn.sigmoid,
scope="spatial_attention_conv"
)
feature_map_with_attention = tf.multiply(feature_map_with_channel_attention, spatial_attention)
return feature_map_with_attention

#example
feature_map = tf.constant(np.random.rand(2,8,8,32), dtype=tf.float16)
feature_map_with_attention = convolutional_block_attention_module(feature_map, 1)

with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
result = sess.run(feature_map_with_attention)
print(result.shape)

kears的map

https://github.com/datalogue/keras-attention/blob/master/visualize.py

# attention map可视化

1. 卷积知识补充

• 9
点赞
• 65
收藏
觉得还不错? 一键收藏
• 3
评论
05-19
03-31 1351
10-05 653
02-28 4759
09-20 2万+
03-16 5万+

### “相关推荐”对你有帮助么？

• 非常没帮助
• 没帮助
• 一般
• 有帮助
• 非常有帮助

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、C币套餐、付费专栏及课程。