Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/wolfstefan/fungi-classification
https://github.com/wolfstefan/fungi-classification
Last synced: 7 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/wolfstefan/fungi-classification
- Owner: wolfstefan
- License: apache-2.0
- Created: 2022-06-02T22:45:15.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2022-06-03T10:41:21.000Z (over 2 years ago)
- Last Synced: 2024-08-02T15:33:00.300Z (3 months ago)
- Language: Python
- Size: 9.15 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: CITATION.cff
Awesome Lists containing this project
README
# Transformer-based Fine-Grained Fungi Classification in an Open-Set Scenario
This repository is targeted towards solving the FungiCLEF 2022 (https://www.kaggle.com/competitions/fungiclef2022/) challenge. It is based on MMClassification (https://github.com/open-mmlab/mmclassification).
Pre-trained models can be found under Releases (https://github.com/wolfstefan/fungi-classification/releases).
## Usage
### Installation
```bash
conda create -n mmcls-fgvc python=3.8 -y
conda activate mmcls-fgvc
conda install pytorch torchvision cudatoolkit=10.2 -c pytorch-lts
pip install -e .
```### Data
The challenge data has to be downloaded and put into _data/fungiclef2022/_.
### Training
```bash
bash tools/dist_train.sh configs/fungi/swin_large_b12x6-fp16_fungi+val_res_384_cb_epochs_6.py 6
```### Inference
```bash
python tools/test_generate_result_pre-consensus_tta.py work_dirs/swin_large_b12x6-fp16_fungi+val_res_384_cb_epochs_6/swin_large_b12x6-fp16_fungi+val-test_res_384_cb_epochs_6.py work_dirs/swin_large_b12x6-fp16_fungi+val_res_384_cb_epochs_6/best_f1_score_epoch_6.pth results.csv
```