https://github.com/creafz/kaggle-carvana
Solution for the Carvana Image Masking Challenge on Kaggle. It uses a custom version of RefineNet with Squeeze-and-Excitation modules implemented in PyTorch. It was a part of the final ensemble that was ranked 23 out of 735 teams (top 4%).
https://github.com/creafz/kaggle-carvana
deep-learning kaggle machine-learning neural-networks pytorch semantic-segmentation
Last synced: about 1 year ago
JSON representation
Solution for the Carvana Image Masking Challenge on Kaggle. It uses a custom version of RefineNet with Squeeze-and-Excitation modules implemented in PyTorch. It was a part of the final ensemble that was ranked 23 out of 735 teams (top 4%).
- Host: GitHub
- URL: https://github.com/creafz/kaggle-carvana
- Owner: creafz
- License: mit
- Created: 2017-10-22T06:35:43.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2017-10-22T16:16:11.000Z (over 8 years ago)
- Last Synced: 2025-04-11T16:25:13.397Z (about 1 year ago)
- Topics: deep-learning, kaggle, machine-learning, neural-networks, pytorch, semantic-segmentation
- Language: Python
- Homepage:
- Size: 535 KB
- Stars: 10
- Watchers: 3
- Forks: 2
- Open Issues: 1