Skip to content

In this project, we created CNNs from scratch and also performed transfer learning to recognize image

Notifications You must be signed in to change notification settings

Fan-Gong/Dogs-vs-Cats-Image-Recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Dogs vs Cats Image Recognition

In this project, we use three neural network models to do image recognition -- Cifar 10, VGG-16 and Inception-V3. These models are implemented to classifiy 12500 cat/dog images. The prediction performance of three model has ranking of 65%, top 6.6%, top 5.3% in the Kaggle competition respectively. Based on that, we also compare the models and get some interesting findings of the results.

Project summary:

a

Project Conclusion

b

  • Kaggle Best Ranking

Our best model ranked top 5.3% in kaggle competition, here are the screenshots: b1 b2

Following suggestions by RICH FITZJOHN (@richfitz). This folder is orgarnized as follows.

proj/
├── lib/
├── data/
├── doc/
├── figs/
└── output/

Please see each subfolder for a README file.

About

In this project, we created CNNs from scratch and also performed transfer learning to recognize image

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published