当前位置:网站首页>ByteDance open source Gan model compression framework, saving up to 97.8% of computing power - iccv 2021
ByteDance open source Gan model compression framework, saving up to 97.8% of computing power - iccv 2021
2022-07-06 16:49:00 【ByteDance Technology】
Put the outline of the shoes :
Restore to the shoe body :
How much calculation is needed ?
Use the most basic Pix2Pix Model , Need to consume 56.8G;
And when Pix2Pix The model is compressed by a new technology , It only needs 1.219G, It's the original 1/46.6, It greatly saves the amount of calculation .
The technology used here , That is, the technical team of ByteDance will meet at the top of computer vision ICCV 2021 Published on Online multi particle Distillation Algorithm (Online Multi-Granularity Distillation, abbreviation OMGD).
This model compression framework , To govern GAN The volume of the model is too large 、 Too much calculation effort , At present, the code is open source ( The address is at the end of the article ), as well as CycleGAN And Pix2Pix Pre training model of , And it has been landing on products such as Tiktok .
Compared with similar model compression algorithms ,OMGD This new framework , Not only the pressure is smaller , And the pressure is better .
For example, in the process of turning horses into zebras :
MACs Indicates the amount of calculation consumed , The number in brackets is the promotion multiple
And turning summer into winter :
Restore the divided street view into photos ( Pay attention to the cyclist ):
Experiments show that , This technology can make GAN The calculation amount of the model is reduced to the original 1/46、 The minimum number of parameters is reduced to the original 1/82.
Convert it , Is to omit 97.8% Amount of computation .
OMGD How did it happen
Model compression usually uses 「 Distillation of knowledge 」 Methods , That is, there are many parameters 、 The bulky model acts as 「 Teacher model 」, There are few parameters to supervise and optimize 、 Small size 「 Student model 」, Let the student model get the knowledge taught by the teacher model without expanding the volume .
OMGD This technology optimizes a student model by two teacher models that complement each other in the width and depth of the neural network , whole Pipeline That's true :
The framework transfers the concepts of different levels from the middle layer and the output layer , It can be used without discriminator and without Ground Truth Training under the setting of , Realize the refinement of knowledge , The on-line distillation scheme was optimized as a whole .
stay Pix2Pix and CycleGAN Experimental data on two well-known models show ,OMGD You can use the least number of parameters 、 The lowest amount of computation achieves the best image generation effect .
The most the right side FID The smaller the score , Indicates that the better the generation effect
Why make the big model smaller ?
ByteDance technical team related research and development students said , This is the first online knowledge distillation to compress GAN Technical solution , Has landed in Tiktok .
you 're right , All kinds of funny special effects props you see in Tiktok , All kinds of algorithm models are needed to run , Especially in dealing with special effects related to images ,GAN It's a general method , This set of GAN The model compression scheme has also been implemented in Tiktok , such as 「 Motion pictures 」:
「 Dance gloves 」:
also 「 Three screen life 」:
however ,GAN Models are usually large , It takes a lot of calculation to complete , It is a great challenge to land on mobile phones, especially low-end computers with insufficient computing power .OMGD A classmate of the R & D team said :“ We will measure the coverage of the model , That is, how many models of a model can run smoothly , After successfully compressing the model, more mobile phones can be covered , Let more people use , If the original model may be iPhone 11 Ability to use , After the compression iPhone 7 Can also be used .”
therefore , Model compression is a rigid requirement , How to make GAN Used by more people 、 Provide more inclusive services , It is the direction that the technology industry has been pursuing .
ByteDance technology team was the first 2017 Research on compression of annual input model , Today's headline 、 Tiktok 、 Cut and reflect 、 Watermelon video, etc App All have relevant technologies , I've also got 2020 year IEEE Low power computer vision challenge (LPCV) The champion of two tracks .
after OMGD Before compression , Teams usually use distillation or pruning algorithms to complete GAN Compression of models , Because the input resolution required by the model is very large , The amount of calculation is still very large , Not compressed to the extreme .
How can we achieve more extreme compression ?
After studying a large number of existing methods in academia , ByteDance technical team students did not find a method suitable for the company's business , Instead, I decided to study by myself , Creatively in GAN In model compression, it is the first time to think of using two complementary teacher models to train the same student model , And achieved the success of the experiment .
Now? ,OMGD In practice, it can be faster than the original method 20~30%, Some can even reach 80%.
also , As can be 「 Online compression 」 Methods ,OMGD Greatly reduced GAN The complexity of model production . there 「 On-line 」 It's not the online state that we refer to in our daily life , It means that the distillation process is completed in one step ,“ Previous GAN The compression method is carried out in several steps , For example, pre training first , Train again after compression , Then there are other steps , It's more complicated as a whole ; Our new method can complete the whole process in one step , The effect is also much better than other methods .” The team technical classmate said .
Now? , This kind of model compression technology can not only save computing power and energy , It can provide users with a smooth experience , Help creators inspire creativity , Enrich your life .
Related links
Address of thesis :
https://arxiv.org/abs/2108.06908
GitHub Code and training model :
https://github.com/bytedance/OMGD
边栏推荐
- Research Report on market supply and demand and strategy of China's four flat leadless (QFN) packaging industry
- LeetCode 1641. Count the number of Lexicographic vowel strings
- LeetCode 1636. Sort the array in ascending order by frequency
- 两个礼拜速成软考中级软件设计师经验
- 字节跳动多篇论文入选 CVPR 2021,精选干货都在这里了
- 7-7 ring the stupid bell
- Error: case label `15 'not within a switch statement
- 腾讯面试算法题
- Erlang installation
- 图像处理一百题(11-20)
猜你喜欢
I'm "fixing movies" in ByteDance
Solve the problem of intel12 generation core CPU [small core full, large core onlookers] (win11)
Submit several problem records of spark application (sparklauncher with cluster deploy mode)
~83 form introduction
~74 JD top navigation bar exercise
LeetCode 1637. The widest vertical area between two points without any point
Base dice (dynamic programming + matrix fast power)
Chapter III principles of MapReduce framework
Gridhome, a static site generator that novices must know
解决Intel12代酷睿CPU【小核载满,大核围观】的问题(WIN11)
随机推荐
7-6 sum of combinatorial numbers
业务系统兼容数据库Oracle/PostgreSQL(openGauss)/MySQL的琐事
Chapter III principles of MapReduce framework
Spark的RDD(弹性分布式数据集)返回大结果集
第7章 __consumer_offsets topic
两个礼拜速成软考中级软件设计师经验
Basic principles of video compression coding and audio compression coding
Solr standalone installation
Market trend report, technical innovation and market forecast of double-sided foam tape in China
Solr word segmentation analysis
Redis standalone startup
~75 background
(lightoj - 1323) billiard balls (thinking)
~71 abbreviation attribute of font
Spark's RDD (elastic distributed data set) returns a large result set
软通乐学-js求字符串中字符串当中那个字符出现的次数多 -冯浩的博客
Chapter 6 datanode
字节跳动开源GAN模型压缩框架,算力最高节省97.8%丨ICCV 2021
SQL快速入门
Mp4 format details