Comments (2)
Hi @dydxdt ,
config中提供的 configs/strategies/MBV2/mbv2.yaml 策略,是用于mbv2 imagenet训练的baseline策略,其精度大约在73.3%。使用 configs/strategies/MBV2/mbv2_se_aa.yaml能得到约74.3%的精度,算是目前mbv2比较高的精度了。
同样,在resnet上,configs/strategies/resnet/resnet.yam 是与torchvision一致的baseline训练策略,精度大约在76.1%。configs/strategies/resnet/seresnext.yaml 会更强一些,大约能到78.5%。
对于你自己的数据集,这部分在imagenet上较高精度的策略不一定对你的任务最优。策略的调整取决于数据集大小、任务难度等特性,需要进行一些调参。
from image_classification_sota.
感谢~
from image_classification_sota.
Related Issues (10)
- Hello Author, I found the edgenn package in the nas_model.py and builder.py is missing,Can you provide a solution HOT 2
- [Question] Could I use DIST in RetinaFace? HOT 5
- lack edgenn model HOT 1
- replace the dbb block
- about the dimension HOT 3
- ddim_loss不收敛,是怎么回事 HOT 2
- (dataset problem) ImageNet has not "meta/train.txt" HOT 1
- How to write the transformer decoder? HOT 2
- split global token and image token HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from image_classification_sota.