当前位置:网站首页>Full details of efficientnet model
Full details of efficientnet model
2022-07-07 14:32:00 【Xiaobai learns vision】
Click on the above “ Xiaobai studies vision ”, Optional plus " Star standard " or “ Roof placement ”
Heavy dry goods , First time delivery
Reading guide
This paper introduces an efficient network model EfficientNet, And analyzed EfficientNet B0 to B7 The differences between the network structures .
I'm in a Kaggle Read in the competition notebooks, It turns out that almost everyone is using EfficientNet As their backbone , And I've never heard of this before .
Google AI In this article :https://arxiv.org/abs/1905.11946 Introduced it , They tried to come up with a more efficient method , As its name suggests , At the same time, it improves the latest results . Generally speaking , The model is designed too wide , Too deep , Or the resolution is too high . At the beginning , Adding these features is useful , But it will soon be saturated , Then the parameters of the model will be many , So the efficiency is not high . stay EfficientNet in , These features are extended in a more principled way , in other words , Everything is gradually increasing .
I don't understand what happened ? Don't worry about , Once you see the architecture , You will understand . But first of all , Let's see what they got .
Because the number of parameters is quite small , This model family is very efficient , Also provide better results . Now we know why these may become standard pre training models , But something is missing .
something in common
First , Any network takes it as the backbone , After that , All experiments on architecture start with it , This is in all 8 The two models are the same as in the last layer .
after , Each trunk contains 7 individual block. these block There are different numbers of children block, These block The number goes with EfficientNetB0 To EfficientNetB7 And increase . To visualize the model layer , The code is as follows :
!pip install tf-nightly-gpu
import tensorflow as tf
IMG_SHAPE = (224, 224, 3)
model0 = tf.keras.applications.EfficientNetB0(input_shape=IMG_SHAPE, include_top=False, weights="imagenet")
tf.keras.utils.plot_model(model0) # to draw and visualize
model0.summary() # to see the list of layers and parameters
If you calculate EfficientNet-B0 The total number of floors , The total number is 237 layer , and EfficientNet-B7 The total number of is 813 layer !! But don't worry , All of these layers can be made up of 5 It consists of three modules and the upper trunk .
We use this 5 Two modules to build the whole structure .
modular 1 — This is the son block The starting point of the .
modular 2 — This module is used for all modules except the first module 7 The first sub module of the first main module block The starting point of the .
modular 3 — It's connected to all the children as a jump block.
modular 4 — Used to merge jump connections into the first child block in .
modular 5 — Each child block Are connected to the previous child by jumping connection block, And use this module for combination .
These modules are further combined into sub modules block, These block Will be in block To use in some way .
Son block1 — It is only used for the first block The first child in block.
Son block2 — It is used for all other block The first child in block.
Son block3 — For all block Any child except the first one in block.
up to now , We have specified to combine to create EfficientNet All the contents of the model , So let's start .
Model structure
EfficientNet-B0
EfficientNet-B0 framework .(x2 Indicates that the module in parentheses is repeated twice )
EfficientNet-B1
EfficientNet-B1 Structure
EfficientNet-B2
Its architecture is the same as the above model , The only difference is the characteristic graph ( passageway ) The number of different , Increased the number of parameters .
EfficientNet-B3
EfficientNet-B3 Structure
EfficientNet-B4
EfficientNet-B4 Structure
EfficientNet-B5
EfficientNet-B5 Structure
EfficientNet-B6
EfficientNet-B6 Structure
EfficientNet-B7
EfficientNet-B7 Structure
It's easy to see the differences between the models differences , They gradually increased the number of children block The number of . If you understand the architecture , I encourage you to print out any model , And read it carefully to understand it more thoroughly . The following table shows EfficientNet-B0 Kernel size and resolution of convolution operation in 、 Channels and layers .
This table has been included in the original paper . For the entire model family , The resolution is the same . I'm not sure if the size of the convolution kernel has changed . The number of layers has been shown in the figure above . The number of channels is different , It is calculated from the information seen in the summary of each model , As shown below :
Before the end , I attached another image , Research papers from it , Shows it with other SOTA Of performance Comparison , There are also reduced number of parameters and required FLOPS.
The good news !
Xiaobai learns visual knowledge about the planet
Open to the outside world
download 1:OpenCV-Contrib Chinese version of extension module
stay 「 Xiaobai studies vision 」 Official account back office reply : Extension module Chinese course , You can download the first copy of the whole network OpenCV Extension module tutorial Chinese version , Cover expansion module installation 、SFM Algorithm 、 Stereo vision 、 Target tracking 、 Biological vision 、 Super resolution processing and other more than 20 chapters .
download 2:Python Visual combat project 52 speak
stay 「 Xiaobai studies vision 」 Official account back office reply :Python Visual combat project , You can download, including image segmentation 、 Mask detection 、 Lane line detection 、 Vehicle count 、 Add Eyeliner 、 License plate recognition 、 Character recognition 、 Emotional tests 、 Text content extraction 、 Face recognition, etc 31 A visual combat project , Help fast school computer vision .
download 3:OpenCV Actual project 20 speak
stay 「 Xiaobai studies vision 」 Official account back office reply :OpenCV Actual project 20 speak , You can download the 20 Based on OpenCV Realization 20 A real project , Realization OpenCV Learn advanced .
Communication group
Welcome to join the official account reader group to communicate with your colleagues , There are SLAM、 3 d visual 、 sensor 、 Autopilot 、 Computational photography 、 testing 、 Division 、 distinguish 、 Medical imaging 、GAN、 Wechat groups such as algorithm competition ( It will be subdivided gradually in the future ), Please scan the following micro signal clustering , remarks :” nickname + School / company + Research direction “, for example :” Zhang San + Shanghai Jiaotong University + Vision SLAM“. Please note... According to the format , Otherwise, it will not pass . After successful addition, they will be invited to relevant wechat groups according to the research direction . Please do not send ads in the group , Or you'll be invited out , Thanks for your understanding ~
边栏推荐
- Huawei cloud database DDS products are deeply enabled
- Use case diagram
- GAN发明者Ian Goodfellow正式加入DeepMind,任Research Scientist
- OAuth 2.0 + JWT 保护API安全
- 什么是云原生?这回终于能搞明白了!
- PD虚拟机教程:如何在ParallelsDesktop虚拟机中设置可使用的快捷键?
- 一文读懂数仓中的pg_stat
- Codes de non - retour à zéro inversés, codes Manchester et codes Manchester différentiels couramment utilisés pour le codage des signaux numériques
- ARM Cortex-A9,MCIMX6U7CVM08AD 处理器应用
- The longest ascending subsequence model acwing 482 Chorus formation
猜你喜欢
【立体匹配论文阅读】【三】INTS
UML state diagram
「2022年7月」WuKong编辑器更版记录
The longest ascending subsequence model acwing 482 Chorus formation
Equipment failure prediction machine failure early warning mechanical equipment vibration monitoring machine failure early warning CNC vibration wireless monitoring equipment abnormal early warning
The longest ascending subsequence model acwing 1014 Mountaineering
数据流图,数据字典
Ian Goodfellow, the inventor of Gan, officially joined deepmind as research scientist
2022年13个UX/UI/UE最佳创意灵感网站
Internal sort - insert sort
随机推荐
Cocos creator direction and angle conversion
内部排序——插入排序
Small game design framework
SAKT方法部分介绍
MRS离线数据分析:通过Flink作业处理OBS数据
gvim【三】【_vimrc配置】
oracle 触发器实现级联更新
Decrypt the three dimensional design of the game
Csma/cd carrier monitoring multipoint access / collision detection protocol
多商戶商城系統功能拆解01講-產品架構
大厂做开源的五大痛点
Substance Painter笔记:多显示器且多分辨率显示器时的设置
NLLB-200:Meta开源新模型,可互译200种语言
属性关键字ServerOnly,SqlColumnNumber,SqlComputeCode,SqlComputed
最长上升子序列模型 AcWing 482. 合唱队形
Search engine interface
「2022年7月」WuKong编辑器更版记录
Demis hassabis talks about alphafold's future goals
Assign a dynamic value to the background color of DataGrid through ivalueconverter
Docker deploy Oracle