https://github.com/Erlemar/wheat

Wheat Detection challenge on Kaggle
https://github.com/Erlemar/wheat

deep-learning hydra kaggle-competition object-detection pytorch pytorch-lightning torchvision

Last synced: 2 days ago
JSON representation

Wheat Detection challenge on Kaggle

• Host: GitHub
• URL: https://github.com/Erlemar/wheat
• Owner: Erlemar
• Created: 2020-05-06T14:50:10.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2023-10-03T21:56:57.000Z (about 1 year ago)
• Last Synced: 2024-08-04T03:11:09.257Z (4 months ago)
• Topics: deep-learning, hydra, kaggle-competition, object-detection, pytorch, pytorch-lightning, torchvision
• Language: Python
• Homepage:
• Size: 73.2 KB
• Stars: 83
• Watchers: 2
• Forks: 13
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# wheat_detection

This is my repository with a baseline model for [Wheat Detection challenge on Kaggle](https://www.kaggle.com/c/global-wheat-detection)

Main frameworks used:

* [hydra](https://github.com/facebookresearch/hydra)

* [pytorch-lightning](https://github.com/PyTorchLightning/pytorch-lightning)

To use it for training, perform the following steps:

* download the data, unzip in and put in some folder;

* define that folder in config conf/data/data.yaml as a value of the key `data.folder_path`

* run run_hydra.py script

There is no script for prediction, because in this competition we have to make prediction in kernels.

Refer to my kernel for more information: https://www.kaggle.com/artgor/object-detection-with-pytorch-lightning