DL之InceptionV4/ResNet：InceptionV4/Inception-ResNet算法的簡介(論文介紹)、架構詳解、案例應用等配圖集合之詳細攻略

?

?

?

目錄

InceptionV4/Inception-ResNet算法的簡介(論文介紹)

1、實驗結果

Inception-v4算法的架構詳解

Inception-ResNet算法的架構詳解

InceptionV4/Inception-ResNet算法的案例應用

---

?

?

?

?

?

?

?

相關文章
DL之InceptionV2/V3：InceptionV2 & InceptionV3算法的簡介(論文介紹)、架構詳解、案例應用等配圖集合之詳細攻略
DL之BN-Inception：BN-Inception算法的簡介(論文介紹)、架構詳解、案例應用等配圖集合之詳細攻略
DL之InceptionV4/ResNet：InceptionV4/Inception-ResNet算法的簡介(論文介紹)、架構詳解、案例應用等配圖集合之詳細攻略
DL之InceptionV4/ResNet：InceptionV4/Inception-ResNet算法的架構詳解之詳細攻略

?

InceptionV4/Inception-ResNet算法的簡介(論文介紹)

? ? ? ?InceptionV4和Inception-ResNet是谷歌研究人員，2016年，在Inception基礎上進行的持續改進，又帶來的兩個新的版本。

Abstract
? ? ? ? Very deep convolutional networks have been central to ?the largest advances in image recognition performance in ?recent years. One example is the Inception architecture that ?has been shown to achieve very good performance at relatively ?low computational cost. Recently, the introduction ?of residual connections in conjunction with a more traditional ?architecture has yielded state-of-the-art performance ?in the 2015 ILSVRC challenge; its performance was similar ?to the latest generation Inception-v3 network. This raises ?the question of whether there are any benefit in combining ?the Inception architecture with residual connections. Here ?we give clear empirical evidence that training with residual ?connections accelerates the training of Inception networks ?significantly. There is also some evidence of residual Inception ?networks outperforming similarly expensive Inception ?networks without residual connections by a thin margin. We ?also present several new streamlined architectures for both ?residual and non-residual Inception networks. These variations ?improve the single-frame recognition performance on ?the ILSVRC 2012 classification task significantly. We further ?demonstrate how proper activation scaling stabilizes ?the training of very wide residual Inception networks. With ?an ensemble of three residual and one Inception-v4, we ?achieve 3.08% top-5 error on the test set of the ImageNet ?classification (CLS) challenge.
摘要
? ? ? ? 非常深的卷積網絡是近年來圖像識別性能最大進步的核心。一個例子是Inception 架構，已經證明它在相對較低的計算成本下獲得了非常好的性能。最近，在2015年的ILSVRC挑戰中，引入residual 連接和更傳統的架構帶來了最先進的性能；其性能類似于最新一代的Inception-v3網絡。這就提出了這樣一個問題：在將Inception 架構與residual 連接結合起來時是否有任何好處。在這里，我們給出了清晰的經驗證據，證明使用residual 連接的訓練顯著加速了初始網絡的訓練。還有一些證據表明，residual Inception 架構網絡的表現優于同樣昂貴的Inception 網絡，而無需residual 連接。我們還為殘差和非殘差初始網絡提供了幾種新的簡化架構。這些變化顯著提高了ILSVRC 2012分類任務的單幀識別性能。我們進一步證明了適當的激活比例如何穩定非常廣泛的residual Inception網絡的訓練。利用三個residual 和一個Inception-v4,的集合，我們在ImageNet分類（CLS）挑戰的測試集上實現了3.08% top-5 錯誤。
Conclusions
? ? ? ?We have presented three new network architectures in detail:
? Inception-ResNet-v1: a hybrid Inception version that has a similar computational cost to Inception-v3 from [15].
? Inception-ResNet-v2: a costlier hybrid Inception version with significantly improved recognition performance.
? Inception-v4: a pure Inception variant without residual connections with roughly the same recognition performance as Inception-ResNet-v2.
? ? ? ?We studied how the introduction of residual connections leads to dramatically improved training speed for the Inception architecture. Also our latest models (with and without residual connections) outperform all our previous networks, just by virtue of the increased model size.
結論
? ? ? ?我們詳細介紹了三種新的網絡架構:
?Inception-ResNet-v1:一個混合的Inception版本，其計算成本與[15]版本的incep -v3相似。
?Inception-ResNet-v2:一個成本更高的混合Inception版本，顯著提高了識別性能。
?Inception-v4:一個沒有residual 連接的Inception，與Inception-ResNet-v2的識別性能大致相同。
? ? ? ?我們研究了如何引入residual 連接來顯著提高Inception體系結構的訓練速度。此外，我們最新的模型(包括和不包括residual 連接)的性能優于所有以前的網絡，這僅僅是因為模型的大小有所增加。

?

1、實驗結果

1、Single crop -single model experimental results Reported on the non-blacklisted subset of the validation set of ILSVRC 2012 單crop -單模型試驗結果：在ILSVRC 2012驗證集的非黑名單子集上的報告
2、144 crops evaluations -single model experimental results 采用了144個crops比single效果更好。 ?
Reported on the all 50000 images of the validation set of ILSVRC 2012 3、Ensemble results with 144 crops/dense evaluation. 集成學習效果更好！ For Inception-v4(+Residual), the ensemble consists of one pure Inception-v4 and three Inception-ResNet-v2 models and were evaluated both on the validation and on the test-set.
4、訓練過程中的速度比較 其中紅色的Inception-resnet-v2效果性能最好 (1)、Top-5 error evolution of all four models (single model, single crop) 模型尺寸較大時，性能改進。 盡管殘差版本收斂得更快，但最終的準確性似乎主要取決于模型的大小。
(2)、Top-1 error evolution of all four models (single model, single crop) This paints a similar picture as the top-5 evaluation. 其中紅色的Inception-resnet-v2效果性能最好

?

?

論文
Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi.
Inception-v4, Inception-ResNetand the Impact of Residual Connections on Learning, 2016
https://arxiv.org/abs/1602.07261

?

Inception-v4算法的架構詳解

DL之InceptionV4/ResNet：InceptionV4/Inception-ResNet算法的架構詳解之詳細攻略

?

Inception-ResNet算法的架構詳解

? ? ? Inception-ResNet網絡： 改進的Inception模塊和殘差連接的結合。引入residual connection直連，把Inception和ResNet結合起來，讓網絡又寬又深。

DL之InceptionV4/ResNet：InceptionV4/Inception-ResNet算法的架構詳解之詳細攻略

?

?

InceptionV4/Inception-ResNet算法的案例應用

后期更新……

?

?

?

?

?

?

?

?

?

?

?

?

?

總結

以上是生活随笔為你收集整理的DL之InceptionV4/ResNet：InceptionV4/Inception-ResNet算法的简介(论文介绍)、架构详解、案例应用等配图集合之详细攻略的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。