https://github.com/cv516buaa/volunet
Science Score: 23.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.9%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: cv516Buaa
- Language: Python
- Default Branch: main
- Size: 1.46 MB
Statistics
- Stars: 1
- Watchers: 1
- Forks: 1
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
A Voronoi Density based Locally Unique Classification Network for Fine-grained Mulitilabel Learning
Binghao Liu
·
Qi Zhao
·
Chunlei Wang
·
Meng Li
·
Lijiang Chen
## Introduction This repo is the implementation of "A Voronoi Density based Locally Unique Classification Network for Fine-grained Mulitilabel Learning"
Voronoi Density based Superpixel Generation Module:
Overview
helper_functions/includes helper functions and dataloader filesloss_functions/includes loss computation filesmodels/includes related model and module
Usage
Dataset
Please prepare related datasets:
- TreeSatAI: https://zenodo.org/records/6780578
- GeoLifeCLEF: https://www.kaggle.com/competitions/geolifeclef-2024
- FathomNet: https://www.kaggle.com/competitions/fathomnet-out-of-sample-detection
The data split files of these datasets can be found at https://drive.google.com/drive/folders/1Bceu-wIOO4q3Q5wChkF8LmUc0A9YVgZq?usp=sharing
Train and Test
- Use the following command for training with TResNet-L
python train.py \
--img_dir=path_of_images \
--csv_path=path_of_csv_file \
--backbone-name=tresnet_l \
--image-size=224 \
--model-path=path_of_pretrained_weights \
--output-path=path_to_save_checkpoints \
--subsampling \
--sub-h=4 \
--sub-w=4 \
--min-superpixels=6
- Use the following command for testing with TResNet-L
python val.py \
--img_dir=path_of_images \
--csv_path=path_of_csv_file \
--backbone-name=tresnet_l \
--ckpt-path=path_of_model_weights
Citation
If you have any question, please discuss with me by sending email to liubinghao@buaa.edu.cn
References
The code is based on ASL and efficient-kan. Thanks for their great works!
Owner
- Name: cv516Buaa
- Login: cv516Buaa
- Kind: user
- Location: Beijing，China
- Company: Beihang University
- Repositories: 2
- Profile: https://github.com/cv516Buaa
Pattern Recognition and Artificial Intelligence Group Prof.Qi Zhao & Lijiang Chen Dr. Shuchang Lyu & Binghao Liu & Chunlei Wang
GitHub Events
Total
- Push event: 2
Last Year
- Push event: 2