https://github.com/ameeassad/eagleid
Science Score: 26.0%
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
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.1%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: ameeassad
- Language: Jupyter Notebook
- Default Branch: main
- Size: 118 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Usage
train.py -- Train classifier.
inference.py -- Inference without GradCAM visualization (uses trainer.test())
prediction.py -- (GradCAM vizualization on during validation without training (epochs 0))
Place all settings in config file and use train.py --config [config file name here]
## Original solver settings OPT = 'adam' # adam, sgd WEIGHTDECAY = 0.0001 MOMENTUM = 0.9 # only when OPT is sgd BASELR = 0.001 LRSCHEDULER = 'step' # step, multistep, reduceonplateau LRDECAYRATE = 0.1 LRSTEPSIZE = 5 # only when LRSCHEDULER is step LRSTEPMILESTONES = [10, 15] # only when LR_SCHEDULER is multistep
Wandb logging
Set to True in config file.
Directory Structure
```plaintext EagleID/ ├── data/ # Dataset cache and data-related scripts ├── dataset/ # Dataset and annotations for datasets ├── models/ # Model architecture code ├── configs/ # Configuration files (e.g., hyperparameters, dataset info) ├── experiments/ # Logging and experiment management (results, logs, etc.) ├── notebooks/ # Jupyter notebooks for prototyping and demo ├── scripts/ # BASH scripts for running programs ├── utils/ # Utility functions and helper scripts ├── checkpoints/ # Model checkpoints and saved weights ├── results/ #Generated results (e.g., GradCAM outputs, predictions) ├── train.py # Training ├── test.py # Testing ├── prediction.py # Prediction ├── README.md # Project description and usage guide ├── requirements.txt # Dependencies list └── .gitignore # Files to ignore in version control
Owner
- Name: Amee Assad
- Login: ameeassad
- Kind: user
- Repositories: 12
- Profile: https://github.com/ameeassad
GitHub Events
Total
- Push event: 500
Last Year
- Push event: 500
Dependencies
- Pillow ==10.4.0
- PyYAML ==6.0.2
- Shapely ==2.0.6
- addict ==2.4.0
- albumentations ==1.2.0
- chumpy ==0.70
- datasets ==2.14.4
- ffmpeg ==6.1.1
- filelock ==3.14.0
- fsspec ==2024.6.1
- grad-cam ==1.5.2
- huggingface-hub ==0.24.6
- imageio ==2.34.0
- ipykernel ==6.29.3
- ipython ==8.12.3
- ipywidgets ==8.1.2
- json-tricks ==3.17.3
- json_tricks ==3.17.3
- markdown ==3.7
- markdown-it-py ==3.0.0
- matplotlib ==3.9.1
- matplotlib ==3.9.2
- mmcv ==2.1.0
- mmcv ==2.2.0
- mmdet ==3.3.0
- mmengine ==0.10.5
- mmengine ==0.10.4
- mmpose ==1.3.2
- numpy ==1.24.4
- numpy ==1.26.4
- opencv-python ==4.10.0.84
- openmim ==0.3.9
- pandas ==2.0.3
- pandas ==2.2.2
- pickleshare ==0.7.5
- pillow ==10.4.0
- pip ==24.2
- psutil ==5.9.8
- pycocotools ==2.0.8
- python-dateutil ==2.9.0.post0
- python-slugify ==8.0.4
- pytorch-lightning ==2.4.0
- pytorch-lightning ==2.3.3
- pyzmq ==25.1.2
- requests ==2.28.2
- scikit-image ==0.24.0
- scikit-learn ==1.5.2
- scikit_learn ==1.5.2
- seaborn ==0.13.2
- setuptools ==60.2.0
- shapely ==2.0.5
- six ==1.16.0
- skimage ==0.0
- tabulate ==0.9.0
- terminaltables ==3.1.10
- timm ==1.0.9
- torch ==2.4.0
- torch ==2.4.1
- torchmetrics ==1.4.2
- torchmetrics ==1.4.0.post0
- torchvision ==0.19.1
- torchvision ==0.18.1
- tqdm ==4.66.5
- tqdm ==4.65.0
- traitlets ==5.14.2
- transformers ==4.44.0
- ttach ==0.0.3
- typing-extensions ==4.12.2
- ultralytics ==8.2.98
- xtcocotools ==1.14.3
- yapf ==0.40.2