wanglimin / places205-vggnet Goto Github PK
View Code? Open in Web Editor NEWPlaces205-VGGNet models for scene recognition
Places205-VGGNet models for scene recognition
Hello,I've been using your model 'siat_scene_vgg_16.model'. I extract fc6 features and normalize them with L2 -norm. Then I use Linear SVM to train the data. But, I get only 12% accuracy in test datasets. I guess that may be the features extract in fc6 is sparse(i.e. Each of these features has a lot of number 'zero'). How can I solve this problem?
Can you also share the models and prototxts for MIT67 and SUN397 datasets?
I am a little confused about the performance on the MIT67 and SUN397 dataset, Is that TOP 1 or TOP 5 rates?
Hi,thanks for you useful model.But I am not so sure for the substracted mean value when training.Can you show me the trainval prototxt?Thanks a lot.
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.