l0sg / wpi_2 Goto Github PK
View Code? Open in Web Editor NEWWeekly Paper Implementation Team
Weekly Paper Implementation Team
training을 해도 loss 값의 변화가 없어서 모델을 하나의 convolution layer, pooling layer, dense-layer로 해놓고 cifar-10 data로 돌려보니 여전히 loss변화가 없었습니다.
그런데 learning rate를 1/10로 줄였더니 처음엔 loss 변화가 거의 없다가 갑자기 크게 감소하여
accuracy가 70프로까지 올라가는 것을 확인하였습니다.
왜 learning rate를 줄이면 loss값에 변화가 있는지 잘 모르겠습니다.
vgg.py의 vgg11 class 내의 build 함수에서 self.images를 처음 convolution layer의 input으로 사용하는데 정의되어 있지 않습니다.
main.py에서 불러온 data를 vgg.py의 train에서 가져와서 feed_dict로 feeding 하는 것으로 보이며
이 data를 tensorflow graph 상에서 받아서 build된 model에 넣어 줄 placeholder가 필요할 것 같습니다.
Cheer up!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.