https://github.com/soumith/galaxyzoo
Entry for GalaxyZoo challenge
https://github.com/soumith/galaxyzoo
Last synced: 8 months ago
JSON representation
Entry for GalaxyZoo challenge
- Host: GitHub
- URL: https://github.com/soumith/galaxyzoo
- Owner: soumith
- License: other
- Created: 2014-03-20T23:32:20.000Z (almost 12 years ago)
- Default Branch: master
- Last Pushed: 2014-11-01T17:41:27.000Z (about 11 years ago)
- Last Synced: 2025-04-30T18:07:20.550Z (8 months ago)
- Language: Lua
- Homepage:
- Size: 437 KB
- Stars: 35
- Watchers: 5
- Forks: 11
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-machine-master - Training a Convnet for the Galaxy-Zoo Kaggle challenge(CUDA demo)
- awesome-machine-learning - Training a Convnet for the Galaxy-Zoo Kaggle challenge(CUDA demo)
- awesome-machine-learning - Training a Convnet for the Galaxy-Zoo Kaggle challenge(CUDA demo)
- awesome-machine-learning - Training a Convnet for the Galaxy-Zoo Kaggle challenge(CUDA demo)
- fucking-awesome-machine-learning - Training a Convnet for the Galaxy-Zoo Kaggle challenge(CUDA demo)
- awesome-machine-learning - Training a Convnet for the Galaxy-Zoo Kaggle challenge(CUDA demo)
- awesome-machine-learning - Training a Convnet for the Galaxy-Zoo Kaggle challenge(CUDA demo)
- awesome-machine-learning-cn - 官网
- awesome-machine-learning - Training a Convnet for the Galaxy-Zoo Kaggle challenge(CUDA demo)
- awesome-advanced-metering-infrastructure - Training a Convnet for the Galaxy-Zoo Kaggle challenge(CUDA demo)
README
galaxyzoo
=========
Entry for GalaxyZoo Challenge:
http://www.kaggle.com/c/galaxy-zoo-the-galaxy-challenge
Our best score was 0.08246 placing us at 9th position, we trained the network for about 6 days, 4 models with different random seeds were trained on 2 NVidia Titan cards.
The model that was trained for entry is in 2_model.lua
The winning model was Sander Dieleman's convnet appropach described here: http://benanne.github.io/2014/04/05/galaxy-zoo.html
For install instructions, please look at INSTALL.md