11
7

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 3 years have passed since last update.

【CNN】1x1 convolutionって何してんの?

Last updated at Posted at 2020-09-26

1x1convolutionってたまに見かけるけど何の為にしてんの?

概要

![image.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/482094/0e89978d-3e0a-de42-71e9-be4645027bb4.png) 入力画像のサイズを変えずにチャネル方向のみに畳み込みをする

image.png
28x28x192のinputに28x28x192のfilter32個を掛け合わせると、28x28x32の出が得られる!

出力チャネル数が減った事により計算量を削減できる!

入力28x28x192 出力28x28x192とする

3x3 convの場合

(28x28x192) x (3x3x192) = 260,112,384

1x1 conv(half channel) => 3x3 convの場合

(28x28x192) x (1x1x96) + (28x28x96) x (3x3x192) = 14,450,688 + 130,056,192 = 144,506,880

参考文献

Network In Network https://arxiv.org/pdf/1312.4400.pdf 1×1 Convolution https://axa.biopapyrus.jp/deep-learning/cnn/1x1_convolution.html A Comprehensive Tutorial to learn Convolutional Neural Networks from Scratch (deeplearning.ai Course #4) https://www.analyticsvidhya.com/blog/2018/12/guide-convolutional-neural-network-cnn/
11
7
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
11
7

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?