# 目录

## 参考资料

 使用非对称卷积分解大filters

InceptionV3中在网络较深的位置使用了非对称卷积，他的好处是在不降低模型效果的前提下，缩减模型的参数规模，在《深度学习面试题27：非对称卷积(Asymmetric Convolutions)》中介绍过。

      end_point = 'Mixed_6d'
with tf.variable_scope(end_point):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, depth(192), [1, 1], scope='Conv2d_0a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1')
branch_1 = slim.conv2d(branch_1, depth(160), [1, 7],
scope='Conv2d_0b_1x7')
branch_1 = slim.conv2d(branch_1, depth(192), [7, 1],
scope='Conv2d_0c_7x1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, depth(160), [1, 1], scope='Conv2d_0a_1x1')
branch_2 = slim.conv2d(branch_2, depth(160), [7, 1],
scope='Conv2d_0b_7x1')
branch_2 = slim.conv2d(branch_2, depth(160), [1, 7],
scope='Conv2d_0c_1x7')
branch_2 = slim.conv2d(branch_2, depth(160), [7, 1],
scope='Conv2d_0d_7x1')
branch_2 = slim.conv2d(branch_2, depth(192), [1, 7],
scope='Conv2d_0e_1x7')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, depth(192), [1, 1],
scope='Conv2d_0b_1x1')
net = tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])
end_points[end_point] = net
View Code

 重新设计pooling层

 辅助构造器

 使用标签平滑

 参考资料

Rethinking the Inception Architecture for Computer Vision