Inception V4 網路結構:

Figure 7 中的，k=192, l=224, m=256, n=384

Tensorflow Slim 的 Inception V4 定義

"""
Inception V4 網路結構定義.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import tensorflow as tf

from nets import inception_utils

slim =
 
 tf.contrib.slim


def block_inception_a(inputs, scope=None, reuse=None):
  """
  Inception V4 的 Inception-A 模組.
  """
  # By default use stride=1 and SAME padding
  with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d],
                      stride=1, padding='SAME'):
    with tf.variable_scope(
 
scope, 'BlockInceptionA', [inputs], reuse=reuse):
      with tf.variable_scope('Branch_0'):
        branch_0 = slim.conv2d(inputs, 96, [1, 1], scope='Conv2d_0a_1x1')
      with tf.variable_scope('Branch_1'):
        branch_1 = slim.conv2d(inputs, 64, [1, 1], scope='Conv2d_0a_1x1')
        branch_1 = slim.
 
conv2d(branch_1, 96, [3, 3], scope='Conv2d_0b_3x3')
      with tf.variable_scope('Branch_2'):
        branch_2 = slim.conv2d(inputs, 64, [1, 1], scope='Conv2d_0a_1x1')
        branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
        branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0c_3x3')
      with tf.variable_scope('Branch_3'):
        branch_3 = slim.avg_pool2d(inputs, [3, 3], scope='AvgPool_0a_3x3')
        branch_3 = slim.conv2d(branch_3, 96, [1, 1], scope='Conv2d_0b_1x1')
      return tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])


def block_reduction_a(inputs, scope=None, reuse=None):
  """
  Inception V4 的 Reduction-A 模組.
  """
  # By default use stride=1 and SAME padding
  with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d],
                      stride=1, padding='SAME'):
    with tf.variable_scope(scope, 'BlockReductionA', [inputs], reuse=reuse):
      with tf.variable_scope('Branch_0'):
        branch_0 = slim.conv2d(inputs, 384, [3, 3], stride=2, 
												padding='VALID', scope='Conv2d_1a_3x3')
      with tf.variable_scope('Branch_1'):
        branch_1 = slim.conv2d(inputs, 192, [1, 1], scope='Conv2d_0a_1x1')
        branch_1 = slim.conv2d(branch_1, 224, [3, 3], scope='Conv2d_0b_3x3')
        branch_1 = slim.conv2d(branch_1, 256, [3, 3], stride=2,
												padding='VALID', scope='Conv2d_1a_3x3')
      with tf.variable_scope('Branch_2'):
        branch_2 = slim.max_pool2d(inputs, [3, 3], stride=2, padding='VALID',
														scope='MaxPool_1a_3x3')
      return tf.concat(axis=3, values=[branch_0, branch_1, branch_2])


def block_inception_b(inputs, scope=None, reuse=None):
  """
  Inception V4 的 Inception-B 模組.
  """
  # By default use stride=1 and SAME padding
  with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d],
                      stride=1, padding='SAME'):
    with tf.variable_scope(scope, 'BlockInceptionB', [inputs], reuse=reuse):
      with tf.variable_scope('Branch_0'):
        branch_0 = slim.conv2d(inputs, 384, [1, 1], scope='Conv2d_0a_1x1')
      with tf.variable_scope('Branch_1'):
        branch_1 = slim.conv2d(inputs, 192, [1, 1], scope='Conv2d_0a_1x1')
        branch_1 = slim.conv2d(branch_1, 224, [1, 7], scope='Conv2d_0b_1x7')
        branch_1 = slim.conv2d(branch_1, 256, [7, 1], scope='Conv2d_0c_7x1')
      with tf.variable_scope('Branch_2'):
        branch_2 = slim.conv2d(inputs, 192, [1, 1], scope='Conv2d_0a_1x1')
        branch_2 = slim.conv2d(branch_2, 192, [7, 1], scope='Conv2d_0b_7x1')
        branch_2 = slim.conv2d(branch_2, 224, [1, 7], scope='Conv2d_0c_1x7')
        branch_2 = slim.conv2d(branch_2, 224, [7, 1], scope='Conv2d_0d_7x1')
        branch_2 = slim.conv2d(branch_2, 256, [1, 7], scope='Conv2d_0e_1x7')
      with tf.variable_scope('Branch_3'):
        branch_3 = slim.avg_pool2d(inputs, [3, 3], scope='AvgPool_0a_3x3')
        branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1')
      return tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])


def block_reduction_b(inputs, scope=None, reuse=None):
  """
  Inception V4 的 Reduction-B 模組.
  """
  # By default use stride=1 and SAME padding
  with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d],
                      stride=1, padding='SAME'):
    with tf.variable_scope(scope, 'BlockReductionB', [inputs], reuse=reuse):
      with tf.variable_scope('Branch_0'):
        branch_0 = slim.conv2d(inputs, 192, [1, 1], scope='Conv2d_0a_1x1')
        branch_0 = slim.conv2d(branch_0, 192, [3, 3], stride=2,
												padding='VALID', scope='Conv2d_1a_3x3')
      with tf.variable_scope('Branch_1'):
        branch_1 = slim.conv2d(inputs, 256, [1, 1], scope='Conv2d_0a_1x1')
        branch_1 = slim.conv2d(branch_1, 256, [1, 7], scope='Conv2d_0b_1x7')
        branch_1 = slim.conv2d(branch_1, 320, [7, 1], scope='Conv2d_0c_7x1')
        branch_1 = slim.conv2d(branch_1, 320, [3, 3], stride=2,
												padding='VALID', scope='Conv2d_1a_3x3')
      with tf.variable_scope('Branch_2'):
        branch_2 = slim.max_pool2d(inputs, [3, 3], stride=2, padding='VALID',
														scope='MaxPool_1a_3x3')
      return tf.concat(axis=3, values=[branch_0, branch_1, branch_2])


def block_inception_c(inputs, scope=None, reuse=None):
  """
  Inception V4 的 Reduction-C 模組.
  """
  # By default use stride=1 and SAME padding
  with slim.arg_scope([slim.conv2d, slim.avg_pool2d, slim.max_pool2d],
                      stride=1, padding='SAME'):
    with tf.variable_scope(scope, 'BlockInceptionC', [inputs], reuse=reuse):
      with tf.variable_scope('Branch_0'):
        branch_0 = slim.conv2d(inputs, 256, [1, 1], scope='Conv2d_0a_1x1')
      with tf.variable_scope('Branch_1'):
        branch_1 = slim.conv2d(inputs, 384, [1, 1], scope='Conv2d_0a_1x1')
        branch_1 = tf.concat(axis=3, values=[
            slim.conv2d(branch_1, 256, [1, 3], scope='Conv2d_0b_1x3'),
            slim.conv2d(branch_1, 256, [3, 1], scope='Conv2d_0c_3x1')])
      with tf.variable_scope('Branch_2'):
        branch_2 = slim.conv2d(inputs, 384, [1, 1], scope='Conv2d_0a_1x1')
        branch_2 = slim.conv2d(branch_2, 448, [3, 1], scope='Conv2d_0b_3x1')
        branch_2 = slim.conv2d(branch_2, 512, [1, 3], scope='Conv2d_0c_1x3')
        branch_2 = tf.concat(axis=3, values=[
            slim.conv2d(branch_2, 256, [1, 3], scope='Conv2d_0d_1x3'),
            slim.conv2d(branch_2, 256, [3, 1], scope='Conv2d_0e_3x1')])
      with tf.variable_scope('Branch_3'):
        branch_3 = slim.avg_pool2d(inputs, [3, 3], scope='AvgPool_0a_3x3')
        branch_3 = slim.conv2d(branch_3, 256, [1, 1], scope='Conv2d_0b_1x1')
      return tf.concat(axis=3, values=[branch_0, branch_1, branch_2, branch_3])


def inception_v4_base(inputs, final_endpoint='Mixed_7d', scope=None):
  """
  給定網路最終節點 final_endpoint，Inception V4 網路建立.

  Args:
    inputs: a 4-D tensor of size [batch_size, height, width, 3].
    final_endpoint: specifies the endpoint to construct the network up to.
      It can be one of [ 'Conv2d_1a_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3',
      'Mixed_3a', 'Mixed_4a', 'Mixed_5a', 'Mixed_5b', 'Mixed_5c', 'Mixed_5d',
      'Mixed_5e', 'Mixed_6a', 'Mixed_6b', 'Mixed_6c', 'Mixed_6d', 'Mixed_6e',
      'Mixed_6f', 'Mixed_6g', 'Mixed_6h', 'Mixed_7a', 'Mixed_7b', 'Mixed_7c',
      'Mixed_7d']
    scope: Optional variable_scope.

  Returns:
    logits: the logits outputs of the model.
    end_points: the set of end_points from the inception model.

  Raises:
    ValueError: if final_endpoint is not set to one of the predefined values,
  """
  end_points = {}

  def add_and_check_final(name, net):
    end_points[name] = net
    return name == final_endpoint

  with tf.variable_scope(scope, 'InceptionV4', [inputs]):
    with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
                        stride=1, padding='SAME'):
      # 299 x 299 x 3
      net = slim.conv2d(inputs, 32, [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_3x3')
      if add_and_check_final('Conv2d_1a_3x3', net): return net, end_points
      # 149 x 149 x 32
      net = slim.conv2d(net, 32, [3, 3], padding='VALID', scope='Conv2d_2a_3x3')
      if add_and_check_final('Conv2d_2a_3x3', net): return net, end_points
      # 147 x 147 x 32
      net = slim.conv2d(net, 64, [3, 3], scope='Conv2d_2b_3x3')
      if add_and_check_final('Conv2d_2b_3x3', net): return net, end_points
      # 147 x 147 x 64
      with tf.variable_scope('Mixed_3a'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='MaxPool_0a_3x3')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 96, [3, 3], stride=2, padding='VALID', scope='Conv2d_0a_3x3')
        net = tf.concat(axis=3, values=[branch_0, branch_1])
        if add_and_check_final('Mixed_3a', net): return net, end_points

      # 73 x 73 x 160
      with tf.variable_scope('Mixed_4a'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
          branch_0 = slim.conv2d(branch_0, 96, [3, 3], padding='VALID', scope='Conv2d_1a_3x3')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
          branch_1 = slim.conv2d(branch_1, 64, [1, 7], scope='Conv2d_0b_1x7')
          branch_1 = slim.conv2d(branch_1, 64, [7, 1], scope='Conv2d_0c_7x1')
          branch_1 = slim.conv2d(branch_1, 96, [3, 3], padding='VALID',  scope='Conv2d_1a_3x3')
        net = tf.concat(axis=3, values=[branch_0, branch_1])
        if add_and_check_final('Mixed_4a', net): return net, end_points

      # 71 x 71 x 192
      with tf.variable_scope('Mixed_5a'):
        with tf.variable_scope('Branch_0'):
          branch_0 = slim.conv2d(net, 192, [3, 3], stride=2, padding='VALID', scope='Conv2d_1a_3x3')
        with tf.variable_scope('Branch_1'):
          branch_1 = slim.max_pool2d(net, [3, 3] 
 

            
  
           

              
              
            
            
相關推薦
			   
            
            
            
 

    

    
    
網路結構之 Inception V4
     
 
							
							
							

Inception V4 網路結構:




Figure 7 中的，k=192, l=224, m=256, n=384

Tensorflow Slim 的 Inception V4 定義

"""
Inception V4 網路結構定義.
"""
fr 

  
 

    

    
    
網路結構之 Inception V3
     
 
							
							
							

1. 卷積網路結構的設計原則(principle)


[1] - 避免特徵表示的瓶頸(representational bottleneck)，尤其是網路淺層結構.
前饋網路可以採用由輸入層到分類器或迴歸器的無環圖(acyclic graph) 來表示，其 

  
 

    

    
    
網路結構解讀之inception系列五：Inception V4
     
 　　在殘差逐漸當道時，google開始研究inception和殘差網路的效能差異以及結合的可能性，並且給出了實驗結構。 
本文思想闡述不多，主要是三個結構的網路和實驗效能對比。 
Inception-v4, Inception-ResNet and  
the Impact of Residual  

  
 

    

    
    
網路結構解讀之inception系列四：Inception V3
     
 　　Inception V3根據前面兩篇結構的經驗和新設計的結構的實驗，總結了一套可借鑑的網路結構設計的原則。理解這些原則的背後隱藏的動機比單純知道這個操作更有意義。 
　　Rethinking the Inception Architecture for Computer Vision 
 
  主題：如何 

  
 

    

    
    
GoogLeNet 之 Inception v1 v2 v3 v4
     
 論文地址 
Inception V1 ：Going Deeper with Convolutions 
Inception-v2 ：Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate 
I 

  
 

    

    
    
Deep Learning-TensorFlow (13) CNN卷積神經網路_ GoogLeNet 之 Inception(V1-V4)
     
 
                

環境：Win8.1 TensorFlow1.0.1

軟體：Anaconda3 （整合Python3及開發環境）

TensorFlow安裝：pip install tensorflow (CPU版) pip install tensorflow-gpu (GPU版)

 

  
 

    

    
    
基於深度學習的病毒檢測技術無需沙箱環境，直接將樣本文件轉換為二維圖片，進而應用改造後的卷積神經網絡 Inception V4 進行訓練和檢測
     
 進制   思科   開發   主題   需求   做的   病毒   無法   大於   話題 3: 基於深度學習的二進制惡意樣本檢測
分享主題：全球正在經歷一場由科技驅動的數字化轉型，傳統技術已經不能適應病毒數量飛速增長的發展態勢。而基於沙箱的檢測方案無法滿足 APT 攻擊的檢測需求，也受到多種反沙箱技術的 

  
 

    

    
    
深度解讀GoogleNet之Inception V1
     
 能力   翻轉   浪費   對齊   並行運算   bubuko   AD   好的   減少   GoogleNet設計的目的
GoogleNet設計的初衷是為了提高在網絡裏面的計算資源的利用率。
Motivation
網絡越大,意味著網絡的參數較多,尤其當數據集很小的時候,網絡更容易發生過擬合。網絡越大 

  
 

    

    
    
【深度學習】GoogLeNet系列解讀 —— Inception v4
     
  
 
 
 
 目錄 
 GoogLeNet系列解讀 
 Inception v1 
 Inception v2 
 Inception v3 
 Inception v4 
 
 簡介 
 在介紹Inception v4之前，首先說明一下Inception v4沒有使用殘差學習的思想。大部分小夥伴對Inc 

  
 

    

    
    
【Network Architecture】Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning（轉） Feature Extractor[Inception v4]
     
 文章來源： https://www.cnblogs.com/shouhuxianjian/p/7786760.html 
 
  Feature Extractor[Inception v4]  
  
  
  
    
   0. 背景 
   隨著何凱明等人提出的ResNet v1，google這邊坐 

  
 

    

    
    
Inception-V1到Inception-V4
     
 
                    GoogLeNet主要思想為Inception結構主要參考了http://caffecn.cn/?/question/255一、題外話;吳恩達老師的深度學習課程講的非常的明白。1.對影象進行卷積是壓縮提取影象特徵資訊的一個過程，構造不同的卷積核提取出的就是不同的特徵。 

  
 

    

    
    
學習筆記：inception V4 與resnet
     
 
                
原始的Inception模型，也就是GoogLeNet被稱為Inception-v1，加入batch normalization之後被稱為Inception-v2，加入factorization的idea之後，改進為Inception-v3。然後發現ResNet的結構可以加 

  
 

    

    
    
Inception-v4與Inception-ResNet結構詳解(原創)
     
 
                

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning，原文連結：https://arxiv.org/pdf/1602.07261.pdf

微軟亞洲研究院的何愷明 

  
 

    

    
    
Kotlin程式設計之Glide V4（使用OkHttp3作為傳輸層）。
     
 
							
							
							Android Glide4 非同步圖片框架





前言：


  Glide預設使用HttpUrlConnection的網路堆疊，也可以使用Google的Volley庫和Squareas的OkHttp庫來替代。




Integration Librar 

  
 

    

    
    
《Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning》筆記
     
 
							
							
							


Inception結構有著良好的效能，且計算量低。Residual connection不同於傳統網路結構，且在2015 ILSVRC取得冠軍，它的效能和Inception-v3接近。作者嘗試將Inception結構和Residual connection 

  
 

    

    
    
【筆記】Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
     
 
                
論文：https://arxiv.org/abs/1602.07261
程式碼：https://github.com/gu-yan/mlAlgorithms/blob/master/inception_impl/Inception_resnet_v2_temsorflow. 

  
 

    

    
    
谷歌Inception網路中的Inception-V3到Inception-V4具體作了哪些優化？
     
 
                
先上Paper列表：[v1] Going Deeper with Convolutions, 6.67% test error, http://arxiv.org/abs/1409.4842[v2] Batch Normalization: Accelerating Dee 

  
 

    

    
    
經典網路結構之InceptionNet
     
  
 
  
  
 InceptionNet又稱googleNet，最初的設計思路是增加網路寬度：InceptionNet核心結構包括多個分支，分別對應不同的感受野。大的感受野適用大的目標，小的感受野適用小目標，如此網路具備了scale不變性。 不同感受野最終通過concat合併在一起，為了避免通道數爆炸， 

  
 

    

    
    
【深度學習】在Dog Breed Identification中使用Inception-V4遇到過擬合的問題解決進展
     
 
								            
						
                
在Plant Seedlings Classification中自己根據谷歌的paper用keras搭建了Inception-V4,但在Plant比賽中因為資料集較簡單，沒有出現過擬合問題，模型成功收斂。但在Dog比賽 

  
 

    

    
    
GoogLeNet 之 Inception-v1 解讀
     
 
                    本篇部落格的目的是展示 GoogLeNet 的 Inception-v1 中的結構，順便溫習裡面涉及的思想。



1 版本主要思想詳述

1.1 Inception v1

    Inception V1 在ILSVRC 2014的比賽中，以較大優勢取得了第一名，