Inception-ResNet-v1實現

Inception V4的網絡結構如下：

Inception-ResNet-v1的總體網絡結構如下所示

從圖中可以看出，輸入部分與V1到V3的輸入部分有較大的差別，這樣設計的目的爲了：使用並行結構、不對稱卷積核結構，可以在保證信息損失足夠小的情況下，降低計算量。結構中1*1的卷積核也用來降維，並且也增加了非線性。 

　　Inception-ResNet-v2與Inception-ResNet-v1的結構類似，除了stem部分。Inception-ResNet-v2的stem與V4的結構類似，Inception-ResNet-v2的輸出chnnel要高。Reduction-A相同，Inception-ResNet-A、Inception-ResNet-B、Inception-ResNet-C和Reduction-B的結構與v1的類似，只不過輸出的channel數量更多。 

Inception-ResNet-v1的Stem與V3的結構是一致的。 
　　接下來主要說一下Inception-ResNet-v1的網絡結構及代碼的實現部分。

Stem結構

　stem結構與V3的Stem結構類似。

對應的代碼爲

with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],stride=1, padding='SAME'):

# 149 x 149 x 32

net = slim.conv2d(inputs, 32, 3, stride=2, padding='VALID', scope='Conv2d_1a_3x3')

end_points['Conv2d_1a_3x3'] = net # 147 x 147 x 32

net = slim.conv2d(net, 32, 3, padding='VALID',scope='Conv2d_2a_3x3')

end_points['Conv2d_2a_3x3'] = net # 147 x 147 x 64

net = slim.conv2d(net, 64, 3, scope='Conv2d_2b_3x3')end_points['Conv2d_2b_3x3'] = net # 73 x 73 x 64

net = slim.max_pool2d(net, 3, stride=2, padding='VALID', scope='MaxPool_3a_3x3')

end_points['MaxPool_3a_3x3'] = net # 73 x 73 x 80

net = slim.conv2d(net, 80, 1, padding='VALID',scope='Conv2d_3b_1x1')

end_points['Conv2d_3b_1x1'] = net # 71 x 71 x 192

net = slim.conv2d(net, 192, 3, padding='VALID',scope='Conv2d_4a_3x3')

end_points['Conv2d_4a_3x3'] = net # 35 x 35 x 256

net = slim.conv2d(net, 256, 3, stride=2, padding='VALID',scope='Conv2d_4b_3x3')

end_points['Conv2d_4b_3x3'] = net

Inception-resnet-A模塊

Inception-resnet-A模塊是要重複5次的，網絡結構爲： 

對應的代碼表示爲：

# Inception-Renset-A

def block35 (net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None) :

"""Builds the 35x35 resnet block."""

with tf.variable_scope(scope, 'Block35', [net], reuse=reuse):

with tf.variable_scope('Branch_0'):

# 35 × 35 × 32

tower_conv = slim.conv2d(net, 32, 1, scope='Conv2d_1x1')

with tf.variable_scope('Branch_1'):

# 35 × 35 × 32

tower_conv1_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1')

# 35 × 35 × 32

tower_conv1_1 = slim.conv2d(tower_conv1_0, 32, 3, scope='Conv2d_0b_3x3')

with tf.variable_scope('Branch_2'):

# 35 × 35 × 32

tower_conv2_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1')

# 35 × 35 × 32

tower_conv2_1 = slim.conv2d(tower_conv2_0, 32, 3, scope='Conv2d_0b_3x3')

# 35 × 35 × 32

tower_conv2_2 = slim.conv2d(tower_conv2_1, 32, 3, scope='Conv2d_0c_3x3')

# 35 × 35 × 96

mixed = tf.concat([tower_conv, tower_conv1_1, tower_conv2_2], 3)

# 35 × 35 × 256

up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None,activation_fn=None, scope='Conv2d_1x1')

# 使用殘差網絡scale = 0.17

net += scale * up

if activation_fn:

net = activation_fn(net)

return net

# 5 x Inception-resnet-A

net = slim.repeat(net, 5, block35, scale=0.17)

end_points['Mixed_5a'] = net

Reduction-A結構

Reduction-A中含有4個參數k、l、 m、 n，它們對應的值分別爲：192, 192, 256, 384，在該層網絡結構，輸入爲35×35×256，輸出爲17×17×896. 

def reduction_a(net, k, l, m, n):

# 192, 192, 256, 384

with tf.variable_scope('Branch_0'):

# 17×17×384

tower_conv = slim.conv2d(net, n, 3, stride=2, padding='VALID',

scope='Conv2d_1a_3x3')

with tf.variable_scope('Branch_1'):

# 35×35×192

tower_conv1_0 = slim.conv2d(net, k, 1, scope='Conv2d_0a_1x1')

# 35×35×192

tower_conv1_0 = slim.conv2d(net, k, 1, scope='Conv2d_0a_1x1')

# 35×35×192

tower_conv1_1 = slim.conv2d(tower_conv1_0, l, 3,

scope='Conv2d_0b_3x3')

# 17×17×256

tower_conv1_2 = slim.conv2d(tower_conv1_1, m, 3,

tower_conv1_0 = slim.conv2d(net, k, 1, scope='Conv2d_0a_1x1')

# 35×35×192

tower_conv1_1 = slim.conv2d(tower_conv1_0, l, 3,

scope='Conv2d_0b_3x3')

# 17×17×256

tower_conv1_2 = slim.conv2d(tower_conv1_1, m, 3,

, scope='Conv2d_0a_1x1')