Tensorflow实现ResNeXt

最新推荐文章于 2022-01-13 18:28:14 发布

David-Chow

最新推荐文章于 2022-01-13 18:28:14 发布

阅读量1.5k

点赞数 3

分类专栏： tensorflow 深度学习编程技巧

本文链接：https://blog.csdn.net/qq_23981335/article/details/103634679

版权

深度学习同时被 3 个专栏收录

54 篇文章 10 订阅

订阅专栏

编程技巧

26 篇文章 0 订阅

订阅专栏

tensorflow

3 篇文章 1 订阅

订阅专栏

ResNeXt-Tensorflow

Code Link

Tensorflow implementation of ResNeXt using Cifar10

If you want to see the original author's code, please refer to this link

（1）Requirements

Tensorflow 1.x
Python 3.x
tflearn (If you are easy to use global average pooling, you should install tflearn)

（2）Issue

If not enough GPU memory, Please edit the code

with tf.Session() as sess : NO
with tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) as sess : OK

（3）Compare Architecture

ResNet

ResNeXt

以下三种表示形式是等效的：

I implemented (b)
(b) is split + transform(bottleneck) + concatenate + transition + merge

（4）Idea

What is the "split" ?

它包含了多个"transform"分支，最后将分支concatenate ，用于实现以下图示中的红框内的模块：

  def split_layer(self, input_x, stride, layer_name):
      with tf.name_scope(layer_name) :
          layers_split = list()
          for i in range(cardinality) :
              splits = self.transform_layer(input_x, stride=stride, scope=layer_name + '_splitN_' + str(i))
              layers_split.append(splits)

          return Concatenation(layers_split)

Cardinality means how many times you want to split.（Cardinality中文即“基数”，英文意思为“the number of elements in a set or other grouping, as a property of that grouping”）

What is the "transform" ?

"transform"是转换，指的是改变输入的外观，它通过很多种手段来改变外观，用于实现以下图示中红框内模块：

 def transform_layer(self, x, stride, scope):
      with tf.name_scope(scope) :
          x = conv_layer(x, filter=depth, kernel=[1,1], stride=stride, layer_name=scope+'_conv1')
          x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
          x = Relu(x)

          x = conv_layer(x, filter=depth, kernel=[3,3], stride=1, layer_name=scope+'_conv2')
          x = Batch_Normalization(x, training=self.training, scope=scope+'_batch2')
          x = Relu(x)
          return x

What is the "transition" ?

"transition"即过渡，意思指的是将自己本身进行改变。通过1x1卷积改变输出通道数目，以与“split”的结果进行merge，用于实现以下红线模块：

  def transition_layer(self, x, out_dim, scope):
      with tf.name_scope(scope):
          x = conv_layer(x, filter=out_dim, kernel=[1,1], stride=1, layer_name=scope+'_conv1')
          x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')

          return x